{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":271,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":271,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"4aff13888555","filters":{"topic":"Stochastic Gradient Optimization Techniques"}},"results":[{"id":"W1522301498","doi":"10.48550/arxiv.1412.6980","title":"Adam: A Method for Stochastic Optimization","year":2014,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":84783,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Mathematical optimization; Computer science; Diagonal; Convergence (economics); Stochastic optimization; Rate of convergence; Optimization problem; Mathematics; Key (lock); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01871386613063046,"gpt":0.2485319222798558,"spread":0.2298180561492253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005002699,0.0003503271,0.0006264208,0.0005694396,0.0002223085,0.00009625836,0.002199625,0.0003871946,0.00004925765],"category_scores_gemma":[0.0001479519,0.0004628222,0.0003201253,0.0003383566,0.0001115098,0.0003277988,0.001900696,0.0002910969,0.000006941858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001621647,"about_ca_system_score_gemma":0.0002265711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001311696,"about_ca_topic_score_gemma":0.00001417021,"domain_scores_codex":[0.9978779,0.0001482451,0.0003026356,0.0009203286,0.0004113468,0.0003395215],"domain_scores_gemma":[0.996911,0.0003400069,0.0007094637,0.001207636,0.0006800198,0.0001518753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004770308,0.00007990128,0.000004534395,0.0002963343,0.0001024842,0.000003601647,0.001731758,0.9580553,0.00001891051,0.02145181,0.002923504,0.01528413],"study_design_scores_gemma":[0.0006399584,0.0001932453,0.00003088517,0.0002710785,0.0001022567,0.000004865395,0.0001304083,0.989318,0.00004762581,0.008305665,0.0005299945,0.0004260092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005417171,0.00005344178,0.9958817,0.0009196664,0.0006145442,0.001184223,0.00009409319,0.0005319989,0.0006662039],"genre_scores_gemma":[0.01294637,0.00001261824,0.9862407,0.0001154768,0.00005780214,0.000008538424,0.0001357409,0.00003125571,0.0004514626],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03126268,"threshold_uncertainty_score":0.9997823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W104184427","doi":"","title":"On the importance of initialization and momentum in deep learning","year":2013,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3536,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Momentum (technical analysis); Computer science; Recurrent neural network; Gradient descent; Stochastic gradient descent; Deep learning; Artificial intelligence; Deep neural networks; Artificial neural network; Schedule; Machine learning; Mathematical optimization; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01169313606498904,"gpt":0.2239115137179905,"spread":0.2122183776530014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001115733,0.00003598959,0.00004335502,0.00006281249,0.00002220192,0.00002911313,0.0001354362,0.00001470777,0.00005504964],"category_scores_gemma":[0.0001078918,0.00002440235,0.000005624786,0.0001983102,0.00002118726,0.0001546258,0.00005310318,0.00003851052,0.000002843429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008172693,"about_ca_system_score_gemma":0.000004095034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002089546,"about_ca_topic_score_gemma":0.000003610316,"domain_scores_codex":[0.9996276,0.00002574763,0.0001106177,0.00009328776,0.00008250206,0.00006023001],"domain_scores_gemma":[0.9996784,0.0001065753,0.00005152134,0.0001159507,0.00003541231,0.00001215435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[3.980789e-7,0.0000121737,0.006798732,0.00000217493,0.000001048733,1.727886e-7,0.0004045431,0.001267452,0.0000965872,0.9894918,0.0001018174,0.001823068],"study_design_scores_gemma":[0.00009688328,0.00007968167,0.01116983,0.00001560464,5.005455e-7,0.000001029738,0.00007039798,0.8980172,0.001653556,0.08882876,0.00001030797,0.00005627003],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05500136,0.00001094665,0.9404649,0.0005269944,0.0000184141,0.0001557479,2.556396e-8,0.00005337382,0.003768196],"genre_scores_gemma":[0.9826511,0.000006136241,0.01704761,0.0002132673,0.000001883739,0.00002671616,3.584272e-7,0.000002152325,0.00005082204],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9276497,"threshold_uncertainty_score":0.09950988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963248893","doi":"10.1007/978-3-319-46128-1_50","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":832,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Convexity; Rate of convergence; Applied mathematics; Mathematics; Stochastic gradient descent; Convergence (economics); Gradient descent; Mathematical proof; Generalization; Simple (philosophy); Convex function; Regular polygon; Mathematical optimization; Computer science; Mathematical analysis; Artificial neural network; Artificial intelligence; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.0238326173554937,"gpt":0.2977316453413589,"spread":0.2738990279858652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001586759,0.0005125259,0.0005615324,0.0007158026,0.0002704163,0.0001600716,0.002441116,0.0002533278,0.00002319874],"category_scores_gemma":[0.0001520445,0.0003400559,0.0001253652,0.0006332943,0.002063059,0.0004388562,0.00123862,0.0004497758,0.000006186121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002160782,"about_ca_system_score_gemma":0.0003265283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000128212,"about_ca_topic_score_gemma":0.000009078291,"domain_scores_codex":[0.9964291,0.0001190356,0.0007206218,0.001328714,0.0008371781,0.00056539],"domain_scores_gemma":[0.9963624,0.001032265,0.0006019445,0.001412737,0.0004192298,0.0001714304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009153763,0.000043007,0.00004992199,0.00006360839,0.00003131322,0.0000108073,0.0009960788,0.00513365,0.0007814504,0.7871828,0.00002433271,0.2056739],"study_design_scores_gemma":[0.0003981699,0.0004960743,0.000267362,0.0007569331,0.00003185753,0.0001553919,0.000001057673,0.4596758,0.02306749,0.5138304,0.0005275907,0.0007918123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007333168,0.0006734192,0.9947411,0.001412275,0.001311917,0.000813456,0.00001191842,0.0001668046,0.0007958202],"genre_scores_gemma":[0.07764057,0.0001702236,0.9206927,0.001022497,0.000163552,0.00003963078,0.000003473948,0.00003794749,0.0002293416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4545422,"threshold_uncertainty_score":0.9999052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951650375","doi":"10.48550/arxiv.1206.5533","title":"Practical recommendations for gradient-based training of deep architectures","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":271,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Debugging; Artificial intelligence; Deep learning; Artificial neural network; Machine learning; Deep neural networks; Context (archaeology); Training (meteorology); Scale (ratio)","retraction":null,"screen_n_in":null,"score":{"opus":0.1800527121404644,"gpt":0.2611330049116545,"spread":0.08108029277119005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003346285,0.0002327799,0.0003013367,0.0004159581,0.0001198353,0.0000425948,0.0009232948,0.00020004,0.00002409459],"category_scores_gemma":[0.0002561188,0.0002706005,0.0002236594,0.0003983235,0.0001203096,0.0001542323,0.000488174,0.0003273503,0.000002737367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001118486,"about_ca_system_score_gemma":0.0002061397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001645229,"about_ca_topic_score_gemma":0.000009031143,"domain_scores_codex":[0.99858,0.0001141639,0.0002611148,0.0006232539,0.00008392167,0.0003374889],"domain_scores_gemma":[0.9977517,0.0006290104,0.000432877,0.0008027812,0.0002286888,0.0001549549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003371569,0.0001991976,0.0001804383,0.00009231453,0.00007884589,0.000006090025,0.0009381456,0.2337192,0.0000156713,0.7610767,0.0004440619,0.003215592],"study_design_scores_gemma":[0.0003871574,0.00008379469,0.00007690728,0.00007093394,0.00008842834,0.000003710893,0.00007618962,0.9288651,0.0005108955,0.06923988,0.0003021808,0.0002947753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001815708,0.00001496172,0.9955443,0.0008042344,0.000478991,0.0005892825,0.00003345155,0.0002962251,0.0004228956],"genre_scores_gemma":[0.6022209,0.000003727624,0.3976063,0.00006345764,0.00002812081,0.000006737325,0.00003196294,0.00001213726,0.00002673642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6951459,"threshold_uncertainty_score":0.9999746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604117713","doi":"10.48550/arxiv.1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":250,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Generalization; Computer science; Artificial neural network; Maxima and minima; Regularization (linguistics); Early stopping; Artificial intelligence; Machine learning; Algorithm; Test data; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1449076541886231,"gpt":0.237001323538144,"spread":0.09209366934952087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003950736,0.0004992738,0.0005068003,0.000314891,0.0006699547,0.0006544911,0.004854295,0.0003130831,0.000001768902],"category_scores_gemma":[0.0001184184,0.0005474736,0.0001328098,0.0003447445,0.0002556049,0.0007589855,0.003103528,0.0004539636,0.000001256409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001657872,"about_ca_system_score_gemma":0.0001704023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008638726,"about_ca_topic_score_gemma":0.00003167336,"domain_scores_codex":[0.9970118,0.00008291841,0.0003086447,0.001811715,0.0001701343,0.0006148114],"domain_scores_gemma":[0.9953762,0.0002151636,0.0007984337,0.003113585,0.0002958303,0.0002008038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003760473,0.00003024236,0.0002115388,0.00003466902,0.00009721989,0.0000518093,0.000473843,0.9752072,0.00000102684,0.02200054,0.00008177815,0.001772517],"study_design_scores_gemma":[0.0006078413,0.0001197526,0.000118839,0.0001449531,0.0001490792,0.00002523192,0.00007298929,0.9947014,0.000005284784,0.003436616,0.000009113763,0.0006089124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01650597,0.00003512931,0.9808604,0.00009569692,0.0007527653,0.0009936951,0.00004700202,0.000639743,0.00006964974],"genre_scores_gemma":[0.8133399,0.00001137197,0.1858486,0.00007663408,0.0001164078,0.000004698823,0.0004725247,0.00004784537,0.00008203855],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7968339,"threshold_uncertainty_score":0.9996977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075660001","doi":"10.1007/s10107-014-0800-2","title":"On the complexity analysis of randomized block-coordinate descent methods","year":2014,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics; Convex function; Separable space; Block (permutation group theory); Convex optimization; Combinatorics; Coordinate descent; Rate of convergence; Convergence (economics); Function (biology); Regular polygon; Sequence (biology); Descent (aeronautics); Convex analysis; Applied mathematics; Mathematical optimization; Computer science; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.05267368180101976,"gpt":0.3311871699736866,"spread":0.2785134881726669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005149773,0.0001515863,0.0007754383,0.0002424474,0.0001089915,0.0001116614,0.0007620528,0.00004657327,0.00004040989],"category_scores_gemma":[0.003678961,0.00008852677,0.0003888361,0.0011814,0.0004049423,0.00005775472,0.0002020074,0.0001204074,0.000007031981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002394137,"about_ca_system_score_gemma":0.000008192895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005275939,"about_ca_topic_score_gemma":3.866273e-7,"domain_scores_codex":[0.9978027,0.0007435334,0.0005740855,0.0002719849,0.0003673269,0.00024037],"domain_scores_gemma":[0.9945124,0.004290627,0.000275504,0.0007217432,0.0001299286,0.00006984491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005467836,0.0001183738,0.000001991212,0.00002013972,0.0002390428,1.925476e-7,0.0004134871,0.000340043,0.00001734136,0.9795969,0.00001240517,0.01918545],"study_design_scores_gemma":[0.001380626,0.0000333488,0.000005244436,0.00002571693,0.0002178633,8.781292e-7,0.00001014635,0.6328008,0.0008000954,0.364635,0.00002017271,0.00007007139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008168597,0.000008067515,0.9955142,0.0008979005,0.0000357045,0.0006780686,3.495782e-7,0.0002404798,0.001808339],"genre_scores_gemma":[0.3785782,3.613583e-7,0.6212274,0.00008218199,0.000004165058,0.00008871078,6.761769e-7,0.00000530046,0.00001291796],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6324608,"threshold_uncertainty_score":0.4404325,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224983028","doi":"10.1109/jas.2022.105506","title":"Cooperative and Competitive Multi-Agent Systems: From Optimization to Games","year":2022,"lang":"en","type":"article","venue":"IEEE/CAA Journal of Automatica Sinica","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Program of Shanghai Academic Research Leader; Project 211; Chinesisch-Deutsche Zentrum für Wissenschaftsförderung; National Natural Science Foundation of China","keywords":"Computer science; Optimization problem; Multi-agent system; Autonomy; Perspective (graphical); Mathematical optimization; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02163397452239797,"gpt":0.2678412780518937,"spread":0.2462073035294957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006226049,0.000181614,0.0004261436,0.000315747,0.0002492744,0.0002483193,0.0007549684,0.00004116354,0.00007190077],"category_scores_gemma":[0.0003192632,0.0001671771,0.00007229201,0.0004920549,0.00006834161,0.0004075918,0.0003041455,0.0002492522,0.000006218218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001855232,"about_ca_system_score_gemma":0.0001823329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001188812,"about_ca_topic_score_gemma":6.600275e-7,"domain_scores_codex":[0.9977003,0.000390146,0.000820336,0.0002880947,0.0005955977,0.0002055221],"domain_scores_gemma":[0.997853,0.0005463886,0.0006073423,0.0003313924,0.0004452794,0.0002166021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000355557,0.0003576992,0.00008331512,0.00001677588,0.0001598541,0.00006808934,0.006177426,0.9695191,0.0004900381,0.01867623,0.003412724,0.001003245],"study_design_scores_gemma":[0.0008245533,0.000867769,0.0003569731,0.0001567527,0.00003872688,0.000179956,0.0008065845,0.9949243,0.0005372123,0.0002362863,0.0008371476,0.0002337105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005660691,0.0002800872,0.9911825,0.001230333,0.0009130093,0.0004194117,0.00003169554,0.0001365159,0.0001457242],"genre_scores_gemma":[0.418173,0.00002696112,0.5812297,0.0004156548,0.00005145457,0.00003609406,0.000002714591,0.00001573871,0.00004858946],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4125124,"threshold_uncertainty_score":0.6817286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2754127623","doi":"10.1007/s11081-017-9366-1","title":"Best practices for comparing optimization algorithms","year":2017,"lang":"en","type":"article","venue":"Optimization and Engineering","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Benchmarking; Best practice; Process (computing); Task (project management); Financial engineering; Optimization algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05613976093467386,"gpt":0.2990190674639251,"spread":0.2428793065292512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000187074,0.0001339136,0.0001428345,0.0001241211,0.000430192,0.0007685301,0.0004337193,0.00006403057,0.000004861592],"category_scores_gemma":[0.0005426955,0.0001465655,0.00002723691,0.00008339115,0.00001956002,0.001349861,0.0001507612,0.0000607948,9.434652e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002475727,"about_ca_system_score_gemma":0.00001565522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000188879,"about_ca_topic_score_gemma":9.991131e-7,"domain_scores_codex":[0.9992228,0.000006771187,0.0001816479,0.0002887057,0.0001164287,0.0001836817],"domain_scores_gemma":[0.9989668,0.00006903446,0.0003274887,0.0004186678,0.0001366421,0.00008140705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001678715,0.00001401377,0.00008574624,0.00002068858,0.000008840594,4.493584e-7,0.00007060734,0.9871783,0.00001927416,0.01060151,0.00002766783,0.001971285],"study_design_scores_gemma":[0.0003259588,0.00003701278,0.00004892371,0.00003996362,0.00001058346,0.0000081959,0.000008808262,0.9987237,0.000169618,0.00003464292,0.0004215892,0.0001710179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005891559,0.00005358195,0.9975969,0.0004025373,0.0003296819,0.0002784219,0.000001588433,0.000314402,0.0009640133],"genre_scores_gemma":[0.02902005,0.0001047507,0.9705471,0.00002552726,0.00006278026,0.00006673351,0.00001268546,0.00001920399,0.0001411471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02896113,"threshold_uncertainty_score":0.7410954,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1772464306","doi":"10.48550/arxiv.1502.04390","title":"Equilibrated adaptive learning rates for non-convex optimization","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Preconditioner; Hessian matrix; Saddle point; Computer science; Mathematical optimization; Rate of convergence; Curvature; Eigenvalues and eigenvectors; Convergence (economics); Stochastic gradient descent; Scheme (mathematics); Adaptive learning; Regular polygon; Convex optimization; Artificial neural network; Artificial intelligence; Applied mathematics; Mathematics; Iterative method; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.09230213855191799,"gpt":0.211123693247461,"spread":0.118821554695543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002128585,0.0001427433,0.0001491755,0.0001981706,0.0001252055,0.00007696296,0.0005728839,0.0000832528,0.00001014058],"category_scores_gemma":[0.0001428082,0.000163866,0.00005525902,0.0008759287,0.00005857089,0.0009301857,0.0001835413,0.00009619129,0.00001966904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062144,"about_ca_system_score_gemma":0.0001180269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195665,"about_ca_topic_score_gemma":8.777441e-7,"domain_scores_codex":[0.9990431,0.00005872872,0.0001256096,0.0004647235,0.0000641186,0.0002437404],"domain_scores_gemma":[0.9989008,0.0001195707,0.0001329519,0.0002912162,0.0003993879,0.0001560635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003336601,0.00002483443,0.0003941544,0.000002564936,0.00001413687,0.000007282842,0.0001990233,0.8871418,0.00002578929,0.1117157,0.0003393031,0.0001021131],"study_design_scores_gemma":[0.0006934644,0.0002868574,0.00001716607,0.00001417664,0.00001294706,0.000001999273,0.0001487431,0.9905705,0.001035232,0.006966951,0.00005998023,0.0001919615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003586958,0.000007729024,0.9937822,0.00005023585,0.0001545047,0.0003462391,0.000001644245,0.0005067092,0.001563768],"genre_scores_gemma":[0.8511732,0.000005190185,0.1479545,0.00005426109,0.00002081063,0.000002961497,0.00001241062,0.00001347224,0.0007632221],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8475862,"threshold_uncertainty_score":0.6682262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1844261860","doi":"10.48550/arxiv.1301.3584","title":"Revisiting Natural Gradient for Deep Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind; Compute Canada","keywords":"Natural (archaeology); Computer science; Artificial intelligence; Geology; Paleontology","retraction":null,"screen_n_in":null,"score":{"opus":0.04715239288676829,"gpt":0.1881851438096175,"spread":0.1410327509228492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002488052,0.0003465981,0.0003519737,0.0002758539,0.0002116942,0.0002280116,0.001957289,0.000267423,0.00001321476],"category_scores_gemma":[0.00009892904,0.0003957014,0.0002755234,0.0004758696,0.00007775766,0.0003771284,0.001685899,0.0004950552,0.00001607843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000252219,"about_ca_system_score_gemma":0.00006220053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003325224,"about_ca_topic_score_gemma":0.000002876273,"domain_scores_codex":[0.9979527,0.0000740993,0.0002665358,0.001144244,0.00007977324,0.0004826764],"domain_scores_gemma":[0.9977466,0.0002226951,0.0003816529,0.001118056,0.0003707552,0.0001602117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000624485,0.00001864764,0.0001294506,0.00005013058,0.00004381841,0.00001627268,0.00008033736,0.4973638,0.000002297448,0.4992869,0.000436723,0.0025654],"study_design_scores_gemma":[0.0002262465,0.00003177433,0.0001042765,0.0001201419,0.00003961826,0.00000406651,0.00001525059,0.942128,0.00002480735,0.05676876,0.00013593,0.0004011253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004412605,0.0002189185,0.991865,0.0001093403,0.001193246,0.0009543546,0.000004002484,0.0007332132,0.0005092848],"genre_scores_gemma":[0.9029092,0.00008853307,0.09605441,0.0001458479,0.0001881617,0.00001306756,0.00003631434,0.00002676628,0.0005376695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8984966,"threshold_uncertainty_score":0.9998495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2596625124","doi":"","title":"Nearly-tight VC-dimension bounds for piecewise linear neural networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Dimension (graph theory); Upper and lower bounds; Piecewise linear function; Mathematics; Combinatorics; Omega; Piecewise; VC dimension; Function (biology); Range (aeronautics); Artificial neural network; Discrete mathematics; Mathematical analysis; Physics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06326245405350339,"gpt":0.2035452813463818,"spread":0.1402828272928784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001813001,0.0001783839,0.0001772191,0.0001243156,0.0008498697,0.0002551481,0.001543113,0.0001157863,0.00001007241],"category_scores_gemma":[0.00009214447,0.0001939717,0.0001218783,0.0002236338,0.0001544526,0.00103009,0.0004834181,0.0001340228,0.00001279572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006659669,"about_ca_system_score_gemma":0.00003609918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003423592,"about_ca_topic_score_gemma":0.000008474907,"domain_scores_codex":[0.9987994,0.00003246304,0.0001387251,0.0006020685,0.00006690282,0.0003603868],"domain_scores_gemma":[0.9980704,0.00009710233,0.0002185809,0.001262048,0.0001945696,0.0001573526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008181243,0.0001229411,0.003363823,0.00001463848,0.00004554944,0.0001022766,0.0001612596,0.3793272,0.00007724849,0.6112493,0.002362015,0.003091956],"study_design_scores_gemma":[0.0005854048,0.0001429131,0.0007297173,0.00001467289,0.00002047916,0.0000045777,0.00000573312,0.9901335,0.0002104548,0.007505646,0.0004248231,0.0002220599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02722023,0.00001841557,0.9706259,0.0002163787,0.000558419,0.0003144592,0.00000272617,0.0003740714,0.0006693476],"genre_scores_gemma":[0.9717298,0.00001470266,0.02689862,0.0001435604,0.00008850531,0.000001938269,0.000005224355,0.00001564447,0.001102011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445096,"threshold_uncertainty_score":0.7909939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091097978","doi":"10.1145/3452296.3472904","title":"Efficient sparse collective communication and its application to accelerate distributed deep learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"China Scholarship Council; King Abdullah University of Science and Technology","keywords":"Computer science; Focus (optics); Distributed computing; Scale (ratio); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01822701639295126,"gpt":0.2550134356046615,"spread":0.2367864192117102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000160749,0.00008369364,0.0000945494,0.0000761513,0.0002245162,0.0001338069,0.0002849944,0.00003686758,0.00001262745],"category_scores_gemma":[0.000195363,0.00008767386,0.00001479152,0.0009472033,0.00001319125,0.00008277711,0.0003838631,0.00008718074,0.0000189203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009155944,"about_ca_system_score_gemma":0.00004484086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006007157,"about_ca_topic_score_gemma":0.00000692415,"domain_scores_codex":[0.9991888,0.00008406676,0.0001501532,0.0003054307,0.0001366807,0.0001348677],"domain_scores_gemma":[0.9990306,0.000108001,0.0000614565,0.0003451717,0.0003704251,0.00008429617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001549518,0.0002396916,0.0004666215,0.00001678623,0.00003055967,0.000004087422,0.003890876,0.4713096,0.009848181,0.4895434,0.0004953446,0.02413942],"study_design_scores_gemma":[0.0001330144,0.00003221244,0.001407668,0.000009835304,0.000003391091,0.000007677604,0.00006992464,0.9793795,0.01756199,0.0009873527,0.000298539,0.00010889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00885052,0.0001063689,0.9879081,0.001020357,0.00002262635,0.00034299,0.000001530816,0.0003345123,0.001412982],"genre_scores_gemma":[0.8609477,0.0000142908,0.1384776,0.0001894251,0.000004482165,0.0001174979,0.0000234431,0.000005690063,0.0002199313],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8520972,"threshold_uncertainty_score":0.3575236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119200797","doi":"","title":"An Accelerated Proximal Coordinate Gradient Method","year":2014,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematical optimization; Dual (grammatical number); Convergence (economics); Proximal Gradient Methods; Computer science; Convex optimization; Empirical risk minimization; Minification; Coordinate descent; Gradient method; Regular polygon; Stochastic gradient descent; Rate of convergence; Convex function; Applied mathematics; Mathematics; Artificial intelligence; Artificial neural network; Key (lock); Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.02352433827712829,"gpt":0.2919534599160039,"spread":0.2684291216388756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076052,0.000189833,0.0002082965,0.000301076,0.0002847428,0.001492146,0.0007632442,0.00008770596,0.000002449939],"category_scores_gemma":[0.00009459895,0.0001647994,0.00003235304,0.0007069946,0.0000280059,0.007238344,0.0000719946,0.0001371274,0.00002364633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006400134,"about_ca_system_score_gemma":0.00005162963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002623025,"about_ca_topic_score_gemma":2.757803e-7,"domain_scores_codex":[0.9983026,0.0001588907,0.0006036137,0.0002393766,0.0003970419,0.0002984684],"domain_scores_gemma":[0.998418,0.00003922756,0.0004509957,0.00041588,0.0005394079,0.0001364464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002795158,0.0001237305,0.0003372301,0.000615445,0.00001786205,0.000001717552,0.00711765,0.1616512,0.001279597,0.292634,0.00171432,0.5344793],"study_design_scores_gemma":[0.0002466856,0.0001659545,0.0001388558,0.00004923137,0.000003845661,0.00005569261,0.00006820211,0.9953638,0.001340981,0.0004187708,0.001944933,0.0002029996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002102811,0.00001995712,0.9935266,0.0002030271,0.0005048873,0.0004500813,0.000001735399,0.001381279,0.001809616],"genre_scores_gemma":[0.8801066,5.282484e-7,0.1192678,0.0003700078,0.0000561703,0.0001191704,0.00002803806,0.000009885726,0.00004181172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8780038,"threshold_uncertainty_score":0.9995444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2780752111","doi":"10.1007/s10589-020-00220-z","title":"Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods","year":2020,"lang":"en","type":"preprint","venue":"Computational Optimization and Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Iterated function; Stochastic gradient descent; Momentum (technical analysis); Mathematics; Rate of convergence; Stochastic optimization; Applied mathematics; Ball (mathematics); Stochastic approximation; Mathematical optimization; Mathematical analysis; Computer science; Finance; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.03332620874769687,"gpt":0.320718223472419,"spread":0.2873920147247221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003620624,0.0004925378,0.0004996904,0.0003805032,0.000475334,0.0005623339,0.0004602045,0.0002034921,0.00000562027],"category_scores_gemma":[0.0001580089,0.0005460698,0.00008144038,0.0004554356,0.0002414873,0.0002888184,0.001053603,0.0003058405,0.00000127569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167825,"about_ca_system_score_gemma":0.0001922975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006048494,"about_ca_topic_score_gemma":5.745082e-7,"domain_scores_codex":[0.9972152,0.0001078194,0.0006642455,0.001344549,0.0003243297,0.0003439032],"domain_scores_gemma":[0.9975739,0.0005624979,0.0005161942,0.0004285396,0.0005126555,0.0004062199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000112693,0.00008090597,0.000005514848,0.000135982,0.00005134111,2.324287e-7,0.0004054868,0.7572226,0.00001757167,0.2392433,0.0003476399,0.002478132],"study_design_scores_gemma":[0.0006245241,0.0001027439,0.0000784949,0.00007145156,0.00008461512,0.0000216245,0.00004485656,0.8596759,0.00001999902,0.1386963,0.0001515014,0.0004279684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004345071,0.0006967129,0.9871101,0.007204269,0.0001590684,0.004181574,0.0001172377,0.0004604736,0.00002710493],"genre_scores_gemma":[0.02749291,0.00009651434,0.9682357,0.0003606078,0.0001050328,0.003052742,0.000546478,0.00005614126,0.00005382013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1024533,"threshold_uncertainty_score":0.9996991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2597452529","doi":"10.48550/arxiv.1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Rate of convergence; Range (aeronautics); Computation; Convergence (economics); Adaptation (eye); Online machine learning; Descent (aeronautics); Mode (computer interface); Artificial intelligence; Mathematical optimization; Machine learning; Algorithm; Active learning (machine learning); Mathematics; Artificial neural network; Key (lock)","retraction":null,"screen_n_in":null,"score":{"opus":0.08496107352918601,"gpt":0.1946122829403172,"spread":0.1096512094111312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002250457,0.0003200913,0.0002888842,0.0002985101,0.0003481787,0.000228955,0.001690134,0.000181213,0.00000761917],"category_scores_gemma":[0.00008785023,0.0003332429,0.0001051042,0.000265114,0.0001269188,0.0004057326,0.001146629,0.0005909484,0.00001802111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002549296,"about_ca_system_score_gemma":0.0001887902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001329374,"about_ca_topic_score_gemma":0.0000525245,"domain_scores_codex":[0.998225,0.0001380644,0.0001753384,0.001026999,0.0001167675,0.0003178484],"domain_scores_gemma":[0.9976943,0.00006836835,0.0005202572,0.001243565,0.0003156232,0.0001579612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002551047,0.0001186883,0.0008947054,0.00002868877,0.0000612951,0.0001468234,0.00033046,0.912534,0.000007518436,0.08421464,0.00004148088,0.001596187],"study_design_scores_gemma":[0.0003926331,0.0001602288,0.001568159,0.000205117,0.00006521183,0.000007233202,0.00006192622,0.9862784,0.00007932344,0.01056088,0.000209011,0.0004118532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06091542,0.00003321239,0.9369618,0.0001163403,0.0003029696,0.0003523991,0.00000627147,0.0006201742,0.0006914337],"genre_scores_gemma":[0.9497052,0.000136506,0.04877264,0.00003823432,0.00004082975,0.000002253217,0.00004922116,0.00002384554,0.001231235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8887898,"threshold_uncertainty_score":0.999912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2750933313","doi":"","title":"Distributed Second-Order Optimization using Kronecker-Factored Approximations","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic gradient descent; Computer science; Computation; Overhead (engineering); Artificial neural network; Curvature; Algorithm; Machine learning; Scaling; Artificial intelligence; Mathematical optimization; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08007162583441403,"gpt":0.3591140077257221,"spread":0.279042381891308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001893604,0.000195645,0.0001627505,0.0002949791,0.001078124,0.001440318,0.0015179,0.00009151713,0.0008622464],"category_scores_gemma":[0.001527821,0.0002128961,0.00007445255,0.0002123238,0.0001373791,0.001481162,0.0003336147,0.0002978732,0.00005022432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001397017,"about_ca_system_score_gemma":0.000151425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000660471,"about_ca_topic_score_gemma":0.000008406027,"domain_scores_codex":[0.99823,0.00009106645,0.0003743034,0.0005501402,0.000518096,0.0002363415],"domain_scores_gemma":[0.9974115,0.0001326271,0.000560761,0.0008626862,0.0009269862,0.0001054011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001255441,0.000132528,0.004335458,0.000004552681,0.00007767584,0.000007299893,0.000788675,0.5831189,0.0006132371,0.4083272,0.0002231731,0.002358747],"study_design_scores_gemma":[0.0003649997,0.00004021745,0.003976494,0.00004411042,0.000009361835,0.00001207026,0.0001052986,0.990036,0.0004701712,0.004434085,0.0002909507,0.0002162613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003326474,0.000002558586,0.9676248,0.002297752,0.0006009876,0.0002812279,0.00003258543,0.0003038108,0.02552973],"genre_scores_gemma":[0.7061213,0.000008581649,0.2923885,0.00005047815,0.0000594806,0.00005980489,0.0002285741,0.00001625462,0.00106708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7027948,"threshold_uncertainty_score":0.9995963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007755560","doi":"10.1007/s10208-014-9220-1","title":"Improved Bounds on Sample Size for Implicit Matrix Trace Estimators","year":2014,"lang":"en","type":"article","venue":"Foundations of Computational Mathematics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Ciência sem Fronteiras; Natural Sciences and Engineering Research Council of Canada","keywords":"TRACE (psycholinguistics); Estimator; Upper and lower bounds; Gaussian; Matrix (chemical analysis); Unit vector; Monte Carlo method; Probabilistic logic; Multivariate random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.01812313942802826,"gpt":0.3075835547097815,"spread":0.2894604152817533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003884373,0.0001742041,0.0002589968,0.0001997562,0.0002150898,0.0001520132,0.0006070756,0.00006104635,0.0000197088],"category_scores_gemma":[0.002625191,0.0001768271,0.000114069,0.0003806372,0.00007697225,0.0002589796,0.00007451947,0.00006527811,0.00001122508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005904264,"about_ca_system_score_gemma":0.0001111353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005041967,"about_ca_topic_score_gemma":8.71406e-7,"domain_scores_codex":[0.9985908,0.00002645892,0.000570579,0.0002779668,0.0003369539,0.0001972689],"domain_scores_gemma":[0.9921371,0.006449233,0.0003896009,0.0004528547,0.000500246,0.00007093728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000378448,0.000180516,0.000007206542,0.00006606083,0.00002024476,2.84431e-8,0.0002639081,0.07546687,0.00007711651,0.9219153,0.0003069151,0.00169203],"study_design_scores_gemma":[0.0002307332,0.0001515185,0.00009603035,0.00002234969,0.000009044073,0.000002989754,0.000008300345,0.5406338,0.0002023156,0.458372,0.0001750407,0.00009593689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002398886,0.000003643825,0.9955588,0.0005431486,0.0001676599,0.000596743,0.00004152388,0.000274793,0.000414829],"genre_scores_gemma":[0.2274735,3.756116e-7,0.7722277,0.00007305151,0.00002918593,0.0001029938,0.00002863572,0.00001783797,0.00004669142],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4651669,"threshold_uncertainty_score":0.7210799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900457592","doi":"","title":"Deep Nets Don't Learn via Memorization","year":2017,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Memorization; Computer science; Artificial intelligence; Mathematics education; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01166250967440062,"gpt":0.2350985713370607,"spread":0.2234360616626601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006618925,0.0003960781,0.0003649511,0.0004796709,0.001122146,0.001201544,0.003145362,0.0003105792,0.00004038241],"category_scores_gemma":[0.0005720302,0.0004176061,0.0001620698,0.000407892,0.0001631451,0.001732562,0.0009479875,0.0003788025,0.00004414974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003376894,"about_ca_system_score_gemma":0.000145686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002491662,"about_ca_topic_score_gemma":0.0005842545,"domain_scores_codex":[0.9972494,0.0001078801,0.0005121181,0.0007697531,0.0005706617,0.0007902519],"domain_scores_gemma":[0.9956651,0.00008960735,0.0005944917,0.003024285,0.0002693907,0.0003570968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005557673,0.0004768826,0.029959,0.00004949791,0.0001009631,0.0001574151,0.0009766407,0.02702061,0.009118276,0.6630765,0.005377751,0.2636309],"study_design_scores_gemma":[0.0003897391,0.0001417766,0.0180308,0.00003679844,0.00001583447,0.0001112844,0.00001317362,0.9456688,0.01125917,0.02248584,0.001340358,0.0005064768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001225692,0.0002206302,0.9868866,0.005761264,0.0004439383,0.0007633637,0.000003732844,0.002337821,0.002356925],"genre_scores_gemma":[0.4969817,0.00007068028,0.5005857,0.001233404,0.0001111411,0.0002973701,0.00001274312,0.0000512009,0.0006560368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9186481,"threshold_uncertainty_score":0.9998353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798888671","doi":"","title":"Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go?","year":2018,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Constant (computer programming); Applied mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06654015255569296,"gpt":0.3147389566761767,"spread":0.2481988041204837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002790701,0.0002128751,0.00018282,0.0001693396,0.0002202871,0.0007357004,0.0004322325,0.00006523228,0.0001235996],"category_scores_gemma":[0.0007130423,0.0001802949,0.00001975448,0.0001648437,0.0004505068,0.0003654795,0.0001745895,0.0001539945,0.00003476945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970094,"about_ca_system_score_gemma":0.00007151312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001377351,"about_ca_topic_score_gemma":0.00002821358,"domain_scores_codex":[0.9984599,0.00006295521,0.0003585904,0.0004942582,0.0003919046,0.000232375],"domain_scores_gemma":[0.9982053,0.0005078003,0.0001800627,0.0002363386,0.0007482029,0.0001222873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003217587,0.00003480419,0.00001426778,0.000006622837,0.00001754881,0.000007440643,0.0007745401,0.00008187721,0.000327812,0.9290766,0.00008335652,0.06954303],"study_design_scores_gemma":[0.00004212391,0.0001953917,0.00003071262,0.00006210837,0.000006176498,0.00001939813,0.0002440128,0.7577154,0.001589565,0.2397873,0.0001163041,0.0001915195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005296533,0.00001140072,0.9943765,0.00244538,0.0007292287,0.0002269142,0.0001153065,0.0001280323,0.001437597],"genre_scores_gemma":[0.6976997,0.000054228,0.3015374,0.0003408241,0.0001180311,0.00001908534,0.00001298721,0.000009031702,0.0002087329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7576335,"threshold_uncertainty_score":0.7352213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034426742","doi":"","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Softmax function; Mathematics; Applied mathematics; Initialization; Rate of convergence; Bounded function; Entropy (arrow of time); Mathematical optimization; Computer science; Mathematical analysis; Physics; Artificial neural network; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1321246909531475,"gpt":0.2731406912845342,"spread":0.1410160003313867,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003567304,0.0003020602,0.0003461068,0.0001790823,0.0001160491,0.00006247321,0.002896332,0.0001708908,0.00002898299],"category_scores_gemma":[0.0005064196,0.0002690158,0.0002268458,0.001488569,0.0002419018,0.0001246894,0.002165176,0.0003534818,0.00002546409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002986196,"about_ca_system_score_gemma":0.0003453701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001993108,"about_ca_topic_score_gemma":0.00000340089,"domain_scores_codex":[0.9980834,0.0003454876,0.0002599978,0.0008954284,0.0001351267,0.000280528],"domain_scores_gemma":[0.9975074,0.0004341888,0.0004105871,0.001268922,0.0002214426,0.000157437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001358124,0.00004310112,0.0003152688,0.00002647558,0.00005432014,0.0000167864,0.000160422,0.05896636,0.00001554106,0.9397418,0.0003832518,0.0002630985],"study_design_scores_gemma":[0.0001038137,0.00008669919,0.0002976469,0.00005290578,0.00002445584,0.000001568499,0.0000239668,0.449756,0.001350105,0.5480401,0.00006169121,0.0002010802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006197568,0.0000277909,0.9888895,0.001235838,0.0004379664,0.0004204079,0.00002766654,0.0003030064,0.002460226],"genre_scores_gemma":[0.9350761,0.00007126485,0.06426056,0.0004450962,0.00003370449,0.000002808984,0.000004855512,0.00001120441,0.00009437412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9288785,"threshold_uncertainty_score":0.9999762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997709794","doi":"10.1609/aaai.v34i04.5793","title":"On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Implementation; Quantization (signal processing); Compression (physics); Convergence (economics); Compression ratio; Rate of convergence; Data compression; Bounded function; Upper and lower bounds; Algorithm; Data compression ratio; Layer (electronics); Theoretical computer science; Artificial intelligence; Image compression; Mathematics; Telecommunications; Image processing; Engineering; Channel (broadcasting)","retraction":null,"screen_n_in":null,"score":{"opus":0.03833580488631928,"gpt":0.3304518789392912,"spread":0.2921160740529719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003504139,0.00006573868,0.0001239729,0.00003355799,0.0002599969,0.00008478696,0.0003681523,0.00002058279,0.0000355454],"category_scores_gemma":[0.0009501672,0.00003596629,0.00005921442,0.0005676673,0.0001937371,0.00009311883,0.0002044921,0.0001099144,4.992236e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007349863,"about_ca_system_score_gemma":0.00001074953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000824741,"about_ca_topic_score_gemma":0.00000301718,"domain_scores_codex":[0.9991666,0.0002135473,0.000218946,0.0001524965,0.0001533676,0.00009500634],"domain_scores_gemma":[0.9949459,0.00444269,0.0001261837,0.0003427574,0.0001008661,0.00004161599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005248777,0.00001294302,0.001845512,0.000002050125,0.00009172699,3.164477e-8,0.0005091951,0.0005243181,0.000008552465,0.9964286,0.0001005307,0.0004713023],"study_design_scores_gemma":[0.0001591713,0.0001391128,0.007861538,0.000003294297,0.0001886725,3.346608e-7,0.0003001508,0.9220063,0.0006524218,0.06857007,0.00005969944,0.00005923555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001865281,0.000006277202,0.9553685,0.04212432,0.000003350089,0.0003678665,0.00001709843,0.00007797547,0.0001693261],"genre_scores_gemma":[0.8703065,0.000004846775,0.1292831,0.0002815011,0.000004914399,0.00005592612,0.00005900299,0.000003062361,0.00000115897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9278585,"threshold_uncertainty_score":0.1999712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2588576771","doi":"10.1109/allerton.2016.7852337","title":"Anytime coding for distributed computation","year":2016,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Matrix multiplication; Computation; Coding (social sciences); Theoretical computer science; Distributed computing; Latency (audio); Parallel computing; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02263475676915671,"gpt":0.2664820547924679,"spread":0.2438472980233112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001044229,0.00005599808,0.00006135096,0.00005490288,0.00005613345,0.00004532231,0.0002314537,0.00002376549,0.00001054316],"category_scores_gemma":[0.00009916438,0.00003705685,0.00002673818,0.0001450856,0.00001695797,0.000260576,0.00005492393,0.00001002375,0.00001379932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003643908,"about_ca_system_score_gemma":0.00001481867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001071334,"about_ca_topic_score_gemma":2.024356e-7,"domain_scores_codex":[0.9994853,0.00000891597,0.0001170804,0.0001765164,0.00008537597,0.0001268248],"domain_scores_gemma":[0.9994599,0.0002033494,0.00004533448,0.0001408358,0.000111783,0.00003883541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003944966,0.00002572569,0.00007821764,0.000004701474,0.000007391201,4.343207e-7,0.00004065185,0.000235825,0.00335311,0.932003,0.01783248,0.04641447],"study_design_scores_gemma":[0.0008586466,0.0001580073,0.0004242345,0.00003742757,0.00000424856,0.000006869255,0.0000043434,0.861374,0.0353295,0.0997818,0.001786266,0.0002346564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006439385,0.000002876836,0.9968102,0.001669309,0.0001149334,0.0002155922,0.000009508362,0.000648272,0.0004649065],"genre_scores_gemma":[0.3189384,0.000001188354,0.6807306,0.00009889933,0.00001497154,0.00003322622,0.00000650132,0.000003987738,0.0001721954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8611382,"threshold_uncertainty_score":0.1511134,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964106020","doi":"","title":"Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection","year":2015,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Discovery Air (Canada); University of British Columbia","funders":"","keywords":"Gauss; Selection (genetic algorithm); Lipschitz continuity; Coordinate descent; Convergence (economics); Rate of convergence; Computer science; Mathematics; Mathematical economics; Algorithm; Mathematical optimization; Applied mathematics; Artificial intelligence; Key (lock); Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01799212104597355,"gpt":0.219382107153064,"spread":0.2013899861070904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000337475,0.000133305,0.0001213205,0.00007430434,0.000101633,0.0001715713,0.0004741532,0.0000378929,0.00002579864],"category_scores_gemma":[0.00002556383,0.00007380202,0.00003055481,0.000385309,0.00006501769,0.0002951104,0.0001099207,0.00008807873,0.00005511968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004784068,"about_ca_system_score_gemma":0.00005920145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004926018,"about_ca_topic_score_gemma":0.00001798171,"domain_scores_codex":[0.9990162,0.00007388552,0.0001322668,0.0002650946,0.0002945311,0.0002180601],"domain_scores_gemma":[0.9992068,0.00006056397,0.00007915995,0.0003125195,0.0002396128,0.0001013403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001368826,0.0009267715,0.04239178,0.00007327844,0.0004894096,0.00004295299,0.02962475,0.03399855,0.001624256,0.6563554,0.2080092,0.02509475],"study_design_scores_gemma":[0.009181005,0.001324047,0.00386936,0.00007516897,0.00007118405,0.0002159999,0.001228411,0.9120473,0.05356002,0.009409697,0.007917015,0.001100794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005365627,0.00001634844,0.9873879,0.001746892,0.0001680124,0.0003430889,5.55108e-7,0.000497027,0.004474534],"genre_scores_gemma":[0.9332813,0.000002087518,0.0636261,0.0004473582,0.00003221966,0.00004838718,0.000001772345,0.00001172461,0.002549018],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9279157,"threshold_uncertainty_score":0.3009559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962705652","doi":"","title":"Stop wasting my gradients: practical SVRG","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Convergence (economics); Variance (accounting); Computation; Generalization; Rate of convergence; Selection (genetic algorithm); Mathematical optimization; Algorithm; Artificial intelligence; Applied mathematics; Mathematics; Channel (broadcasting)","retraction":null,"screen_n_in":null,"score":{"opus":0.06114805913386867,"gpt":0.3037481648630557,"spread":0.2426001057291871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006100062,0.0001676214,0.0001760611,0.0002552771,0.0001934714,0.00115394,0.000469384,0.00008381435,0.000001284031],"category_scores_gemma":[0.0006864557,0.0001489771,0.00003129127,0.000660646,0.00004203045,0.008841286,0.0001475634,0.0001758286,0.00007374894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388423,"about_ca_system_score_gemma":0.0001890759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001566351,"about_ca_topic_score_gemma":1.504029e-7,"domain_scores_codex":[0.9981592,0.00006812799,0.0006315282,0.0001916249,0.00064577,0.0003037684],"domain_scores_gemma":[0.9982119,0.00005878915,0.0005000603,0.0003121405,0.0007154971,0.000201624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006956046,0.000311449,0.002837243,0.001675547,0.00005803497,0.00003725452,0.05330075,0.1468003,0.0001442708,0.5064913,0.05867814,0.2295962],"study_design_scores_gemma":[0.0003184941,0.00007770128,0.00003629442,0.0001110724,0.000004540357,0.0002226738,0.00064419,0.9930332,0.0001134675,0.0003524507,0.004895522,0.0001903843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001601855,0.00008462458,0.9902751,0.0006812838,0.00105101,0.0003439028,0.000001527997,0.001081457,0.004879282],"genre_scores_gemma":[0.9259959,0.000001468152,0.07315734,0.0004930396,0.0001119354,0.0000906589,0.00001872899,0.00001141229,0.0001195154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9243941,"threshold_uncertainty_score":0.9998829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034995656","doi":"10.24963/ijcai.2020/452","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institute for Advanced Research; University of Pennsylvania","keywords":"Stochastic gradient descent; Gradient descent; Computer science; Artificial neural network; Convergence (economics); Generalization; Closing (real estate); Artificial intelligence; Momentum (technical analysis); Gradient method; Stationary point; Deep learning; Rate of convergence; Algorithm; Mathematical optimization; Mathematics; Key (lock); Law","retraction":null,"screen_n_in":null,"score":{"opus":0.1055841967632464,"gpt":0.3277355163136001,"spread":0.2221513195503537,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003937795,0.00009981739,0.0001501942,0.00007403379,0.00005366315,0.00004224177,0.0004875549,0.00003939924,0.000008393087],"category_scores_gemma":[0.0001122782,0.00007416668,0.00004509626,0.0008933498,0.0000475394,0.0002012235,0.000145482,0.0001077502,2.348321e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002433703,"about_ca_system_score_gemma":0.00001414606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002097626,"about_ca_topic_score_gemma":0.00000621257,"domain_scores_codex":[0.9988931,0.0002352752,0.0003023915,0.0002443737,0.0001435411,0.0001813642],"domain_scores_gemma":[0.9993659,0.0001864254,0.0001269669,0.0002012289,0.00006642377,0.00005301394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004897947,0.00001090212,0.000119838,0.000002404036,0.000006084641,0.000001165029,0.00686337,0.6990012,0.0002317446,0.2447693,0.00003372915,0.04895534],"study_design_scores_gemma":[0.0001115138,0.00008564616,0.0001797404,0.000006975431,0.000003732308,0.000002767476,0.0001954118,0.9956931,0.0008609448,0.002767085,0.00001260511,0.00008051387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002885417,0.0001022791,0.9973274,0.001150827,0.0001267255,0.0002279112,2.138676e-7,0.0001510502,0.0006250878],"genre_scores_gemma":[0.4180883,0.000004112316,0.5812081,0.0006549247,0.00002385149,0.00001166789,0.00000140261,0.000005376681,0.000002277724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4177997,"threshold_uncertainty_score":0.302443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035353486","doi":"","title":"From Local SGD to Local Fixed Point Methods for Federated Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Bottleneck; Computer science; Fixed point; Saddle point; Mathematical optimization; Context (archaeology); Computation; Operator (biology); Saddle; Convergence (economics); Theoretical computer science; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0574492059463758,"gpt":0.363646518265808,"spread":0.3061973123194321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003992518,0.0002450154,0.0002628316,0.0001763913,0.0002124345,0.0004134484,0.000956311,0.00008850271,0.0003439067],"category_scores_gemma":[0.001459432,0.0002472877,0.00009533363,0.0002891062,0.00004625535,0.0002679616,0.0003616457,0.000581141,0.00009905959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001163392,"about_ca_system_score_gemma":0.00008206874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001570004,"about_ca_topic_score_gemma":0.000005742475,"domain_scores_codex":[0.9980202,0.0002641513,0.0003771145,0.0006981961,0.0003642331,0.0002761564],"domain_scores_gemma":[0.9984888,0.0005123981,0.0001821667,0.0001577283,0.0004248221,0.0002340836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002625168,0.00006282399,0.0002845162,0.000009874116,0.0001052132,0.00001251188,0.002969939,0.3183586,0.005747294,0.2053464,0.0005521856,0.4662881],"study_design_scores_gemma":[0.0004891355,0.0005643157,0.00006120176,0.00005304481,0.000005929494,0.000003235907,0.0001953815,0.9820394,0.004326643,0.004924962,0.00707332,0.0002634432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003318938,0.00001355211,0.979477,0.01647852,0.0003497939,0.0003031723,0.000009814375,0.0006987986,0.002337446],"genre_scores_gemma":[0.5398855,0.000002653837,0.4579564,0.00170804,0.00008692869,0.00005509888,0.00008007597,0.00002003043,0.0002052543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6636808,"threshold_uncertainty_score":0.9999979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205547947","doi":"10.1561/2400000036","title":"Acceleration Methods","year":2021,"lang":"en","type":"article","venue":"Foundations and Trends® in Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Agence Nationale de la Recherche","keywords":"Acceleration; Convergence (economics); Momentum (technical analysis); Computer science; Mathematical optimization; Mathematical proof; Quadratic equation; Range (aeronautics); Chebyshev filter; Key (lock); Set (abstract data type); Cover (algebra); Quadratic programming; Mathematics; Applied mathematics; Physics; Mechanical engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03732282273889075,"gpt":0.3584317859963982,"spread":0.3211089632575074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002203123,0.00009695134,0.0001089048,0.0004159558,0.0001456788,0.0003164174,0.0001348189,0.00005991536,0.0001881231],"category_scores_gemma":[0.0001186,0.0001073147,0.00002439456,0.001483738,0.00002578614,0.0008237985,0.00009679588,0.00006976954,0.000002540863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004828972,"about_ca_system_score_gemma":0.0000395339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001023272,"about_ca_topic_score_gemma":0.0000172519,"domain_scores_codex":[0.999067,0.0001157459,0.000249795,0.0003269458,0.0001091171,0.0001314116],"domain_scores_gemma":[0.9993455,0.00008473843,0.00007496371,0.0002829519,0.0001682136,0.00004361569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001712748,0.00009961338,0.0003014397,0.000004756253,0.000009353086,0.000004004908,0.0004491734,0.3486466,0.00008785326,0.3882791,0.0002065581,0.2619099],"study_design_scores_gemma":[0.0002522528,0.00001932472,0.001486048,0.000009752232,0.0000052234,0.0000176111,0.00002081226,0.9906998,0.0005365083,0.006259089,0.0005693543,0.0001242842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009201198,0.00008483176,0.9920828,0.001211379,0.0001909228,0.0000645433,0.000001449118,0.0001678469,0.006104222],"genre_scores_gemma":[0.0388632,0.00007902395,0.9602476,0.0001183538,0.00001891094,0.00004193471,0.0001522939,0.000007939031,0.0004706952],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6420532,"threshold_uncertainty_score":0.4376166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889576094","doi":"","title":"Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization.","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Variance reduction; Gradient descent; Combinatorics; Nabla symbol; Stationary point; Function (biology); Stochastic gradient descent; Applied mathematics; Mathematical analysis; Computer science; Physics; Statistics; Omega","retraction":null,"screen_n_in":null,"score":{"opus":0.02298046378812457,"gpt":0.2619998012515888,"spread":0.2390193374634642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003709342,0.0002352642,0.0002373253,0.0003205022,0.0004947213,0.000979458,0.0006885989,0.000108488,0.000004415297],"category_scores_gemma":[0.0002570219,0.0002210834,0.00005429094,0.0008300742,0.00009180659,0.004002894,0.00008882546,0.00009370263,0.00002295079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535031,"about_ca_system_score_gemma":0.0001620872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076733,"about_ca_topic_score_gemma":3.278502e-7,"domain_scores_codex":[0.9980615,0.0000441304,0.0008001485,0.0003009095,0.0004053446,0.0003879367],"domain_scores_gemma":[0.9973581,0.00007121187,0.0006432846,0.0004220182,0.001369808,0.0001355901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004590099,0.00006301144,0.00001472189,0.000381942,0.00001885456,5.314538e-7,0.004302114,0.9316582,0.0001425887,0.04111437,0.002771439,0.01948634],"study_design_scores_gemma":[0.0004851334,0.0002013199,0.00002544153,0.0001614027,0.000009879445,0.00005136108,0.00008383003,0.9976058,0.000356826,0.0001957928,0.0005703549,0.0002528811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000326094,0.00005515337,0.9949181,0.0003720227,0.00169708,0.001303788,0.000007898361,0.0009371894,0.000382695],"genre_scores_gemma":[0.7961357,0.00000129975,0.2025311,0.000469617,0.0002290507,0.0004639179,0.00005106004,0.00001896998,0.00009930479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7958096,"threshold_uncertainty_score":0.9444937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965944281","doi":"","title":"Tight analyses for non-smooth stochastic gradient descent","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Lipschitz continuity; Stochastic gradient descent; Differentiable function; Combinatorics; Convex function; Gradient descent; Upper and lower bounds; Regular polygon; Discrete mathematics; Applied mathematics; Mathematical analysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04690993015189428,"gpt":0.3102476221312967,"spread":0.2633376919794024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005947166,0.0002354505,0.0002738703,0.0002781158,0.0001679565,0.0001664508,0.0008620302,0.00008204028,0.0001298394],"category_scores_gemma":[0.0003178318,0.0002078406,0.0001164269,0.0002920722,0.00007214987,0.000195667,0.0001487141,0.0002522494,0.0001956096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007927304,"about_ca_system_score_gemma":0.0001055896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002074141,"about_ca_topic_score_gemma":4.294957e-7,"domain_scores_codex":[0.9983742,0.0001141738,0.0002524087,0.0005896972,0.0002756598,0.0003939056],"domain_scores_gemma":[0.9982857,0.0005610347,0.000192769,0.0006202292,0.0002181232,0.0001222132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005276585,0.00007526689,0.00007659453,0.00002195348,0.00002811702,0.000001341607,0.0007526672,0.02500296,0.001196654,0.9558377,0.0002062691,0.0167477],"study_design_scores_gemma":[0.000717464,0.001096972,0.0005848994,0.0002507227,0.00002656131,0.000004572322,0.0001863529,0.9044617,0.002341426,0.08919884,0.0006373452,0.0004931325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006060097,0.00002328467,0.9870684,0.0001723001,0.0004085263,0.0006415672,0.000001672178,0.0004546574,0.005169563],"genre_scores_gemma":[0.9603824,0.000005460807,0.03630149,0.0001837702,0.00003467724,0.0001079622,0.000009469995,0.00002459272,0.002950154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9543223,"threshold_uncertainty_score":0.8475491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995291884","doi":"","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Optimization problem; Computer science; Mathematics; Artificial intelligence; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.06320326867818603,"gpt":0.3032700120988561,"spread":0.2400667434206701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001917566,0.0001869136,0.0001425751,0.0001861039,0.0003224447,0.000503227,0.001254932,0.00006385004,0.0001990982],"category_scores_gemma":[0.001352533,0.0001644581,0.00009417839,0.0004952544,0.00008136855,0.0004111422,0.0002210125,0.0004088208,0.0001007115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006945648,"about_ca_system_score_gemma":0.00009741548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001666061,"about_ca_topic_score_gemma":6.227395e-7,"domain_scores_codex":[0.99802,0.0001480536,0.0003337112,0.0006021139,0.0006866247,0.000209518],"domain_scores_gemma":[0.9985223,0.0003716451,0.0002284579,0.0003629738,0.0003955539,0.0001190827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002099615,0.00005843339,0.0001341532,0.000002571952,0.00002973427,0.000003513849,0.001754393,0.5620769,0.00009895205,0.4330623,0.001407107,0.001350933],"study_design_scores_gemma":[0.0003449806,0.0001809128,0.0001511923,0.00003179136,0.000007048956,0.000006362327,0.0002617584,0.9956653,0.0002161137,0.002643694,0.0003231193,0.000167722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004388406,0.000004617261,0.9272605,0.01681809,0.0002544107,0.0003082803,0.000005340498,0.0004844311,0.05442548],"genre_scores_gemma":[0.8857782,0.00001543948,0.1113962,0.0017518,0.0001103306,0.0001476057,0.00009090768,0.00002125601,0.0006882107],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8853394,"threshold_uncertainty_score":0.6706406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3024230214","doi":"","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Variance reduction; Mathematics; Combinatorics; Nabla symbol; Gradient descent; Function (biology); Stationary point; Reduction (mathematics); Applied mathematics; Mathematical analysis; Computer science; Physics; Geometry; Statistics; Omega","retraction":null,"screen_n_in":null,"score":{"opus":0.01973754399397216,"gpt":0.2620247578532457,"spread":0.2422872138592735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003331871,0.000171312,0.0001702014,0.0002885181,0.0004123488,0.0008373769,0.0004462788,0.0001064783,0.000003614937],"category_scores_gemma":[0.0001797055,0.0001664327,0.00003673452,0.0007467608,0.00007113203,0.005788488,0.00005173993,0.00007497474,0.00002040966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009862714,"about_ca_system_score_gemma":0.0001083669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000981629,"about_ca_topic_score_gemma":1.080362e-7,"domain_scores_codex":[0.9985493,0.00003491454,0.000610432,0.0002356527,0.0003084364,0.0002612604],"domain_scores_gemma":[0.9978238,0.00004020244,0.0005598046,0.0003140578,0.001186244,0.00007592399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003060024,0.00002534037,0.000004109252,0.0002333688,0.000009026398,1.307324e-7,0.002731012,0.934647,0.000129555,0.03290858,0.001582781,0.02769854],"study_design_scores_gemma":[0.0003413812,0.0001602931,0.000007244253,0.0000987974,0.000007233717,0.00007009441,0.0001002607,0.9978948,0.0003478178,0.0002289965,0.0005573545,0.0001856952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000123825,0.00003273881,0.9953254,0.0002966763,0.001796578,0.0009646842,0.00000465808,0.0009518359,0.0005035914],"genre_scores_gemma":[0.7655542,9.968331e-7,0.2332513,0.0002200434,0.0003731412,0.0003832098,0.00006062951,0.00001600419,0.0001404103],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7654304,"threshold_uncertainty_score":0.8074844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389986737","doi":"10.1137/1.9781611977806.ch28","title":"Chapter 28: Subgradient Methods","year":2023,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Subgradient method; Computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1119871231347802,"gpt":0.2978296290613603,"spread":0.1858425059265801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008907375,0.0005238846,0.0006936801,0.0001175913,0.0002819694,0.0001940664,0.0006581479,0.0008079996,0.00001215149],"category_scores_gemma":[0.00003914048,0.0004848743,0.0005601998,0.00003996053,0.0002163043,0.00004120638,0.0005125208,0.000486118,0.00001523972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006256791,"about_ca_system_score_gemma":0.00007400569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.850077e-7,"about_ca_topic_score_gemma":3.46411e-7,"domain_scores_codex":[0.9978765,0.000004588739,0.0006588539,0.000702209,0.0003603659,0.0003974458],"domain_scores_gemma":[0.9980335,0.0005420882,0.0004985719,0.0006512264,0.000105001,0.0001696509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003585969,0.000009397396,1.032517e-8,0.00009055757,0.0001530877,4.387531e-7,0.00117971,0.000003719767,0.00005617593,0.9526296,0.002806386,0.04306731],"study_design_scores_gemma":[0.0006848773,0.0001082593,2.132169e-8,0.0001876675,0.0001548329,0.000006249515,0.00006018203,0.006118124,0.001055881,0.9477555,0.04326235,0.0006060564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001589212,0.00002950433,0.767551,0.0001150452,0.0004174613,0.001613232,0.00004544709,0.0006699233,0.2295568],"genre_scores_gemma":[0.00002392516,0.00003404835,0.8240517,0.0001483852,0.0003320047,0.0003323032,0.0000250049,0.0001260994,0.1749265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0565007,"threshold_uncertainty_score":0.9997603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288079579","doi":"10.1145/3419111.3421299","title":"Semi-dynamic load balancing","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Load balancing (electrical power); Sizing; Distributed computing; Software deployment; Python (programming language); Execution time; Synchronization (alternating current); Key (lock); Parallel computing; Operating system; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.01710817377559423,"gpt":0.2580077198261286,"spread":0.2408995460505344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016897,0.0002484408,0.0002741297,0.0001068327,0.00004891168,0.0002618918,0.001802587,0.0001915722,0.00004812095],"category_scores_gemma":[0.0001400575,0.0002457328,0.0001078947,0.0002657202,0.00002574945,0.0001302765,0.003105916,0.0004538429,0.00009940467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002475215,"about_ca_system_score_gemma":0.0003383614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003942815,"about_ca_topic_score_gemma":0.00000439761,"domain_scores_codex":[0.9981846,0.00003288813,0.0002987093,0.0007905966,0.0004506929,0.0002424647],"domain_scores_gemma":[0.9985126,0.0000609768,0.0001547367,0.0009775311,0.0001645069,0.0001297069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001072001,0.000172799,0.0002652034,0.0006322524,0.0002339725,0.0001499182,0.00464406,0.05999704,0.001648046,0.8331971,0.06182002,0.03722888],"study_design_scores_gemma":[0.00006764023,0.00002293121,0.00006857836,0.00007473749,0.000006541777,0.000007140804,0.000005399111,0.9382932,0.0005342077,0.06025178,0.000379527,0.000288313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005327727,0.00009648428,0.9772368,0.002664782,0.0007888619,0.0003401467,0.000003978568,0.002502964,0.01631267],"genre_scores_gemma":[0.1921351,0.00003142979,0.8059635,0.001073302,0.00005270585,0.0000653751,0.00001512463,0.00002333222,0.0006401294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8782961,"threshold_uncertainty_score":0.9999995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996067004","doi":"","title":"Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Generalization; Gradient descent; Layer (electronics); Artificial neural network; Population; Mathematics; Computer science; Flow (mathematics); Applied mathematics; Mathematical analysis; Artificial intelligence; Geometry; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.08250555733982355,"gpt":0.3510375405511749,"spread":0.2685319832113514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001312739,0.0001351424,0.0001470909,0.0001649575,0.0000999498,0.0001755927,0.0007951525,0.00004185088,0.000217608],"category_scores_gemma":[0.0003583629,0.0001413284,0.00006304714,0.0003961961,0.00005498263,0.0006153673,0.0001458241,0.0002075101,0.00001638034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000325418,"about_ca_system_score_gemma":0.00004535435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003468486,"about_ca_topic_score_gemma":0.000002480527,"domain_scores_codex":[0.9984488,0.0001663813,0.0003780089,0.0004240898,0.0004351533,0.0001475885],"domain_scores_gemma":[0.998717,0.0001016604,0.0002732697,0.0002738909,0.0005111152,0.0001230418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008108605,0.00004148878,0.001728785,0.000002200372,0.00001721742,0.000002271201,0.0009353567,0.5710766,0.00116436,0.4224079,0.00008383945,0.002531901],"study_design_scores_gemma":[0.0002881578,0.0002020057,0.001287945,0.00001896936,0.000006782557,0.000004952465,0.00007738733,0.9932674,0.0009568249,0.003717728,0.0000443369,0.0001275149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007542129,0.000008076632,0.9818614,0.005441787,0.0002940619,0.000184045,0.000002970623,0.0003131048,0.004352426],"genre_scores_gemma":[0.9681268,0.00001566452,0.03074509,0.0007685212,0.0001164217,0.00003347968,0.00007537912,0.00001318772,0.0001055089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9605846,"threshold_uncertainty_score":0.5763205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113717009","doi":"10.1007/s10107-006-0031-2","title":"Large-scale semidefinite programming via a saddle point Mirror-Prox algorithm","year":2006,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Office of Naval Research; National Science Foundation","keywords":"Semidefinite programming; Saddle point; Mathematics; Semidefinite embedding; Algorithm; Scale (ratio); Numerical analysis; Mathematical optimization; Positive-definite matrix; Quadratically constrained quadratic program; Quadratic programming; Mathematical analysis; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01255634044540681,"gpt":0.2442069490326277,"spread":0.2316506085872209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009639736,0.0003987729,0.0004631999,0.0002449166,0.000317045,0.0005634672,0.0009393806,0.0001810822,0.0000572184],"category_scores_gemma":[0.0001476562,0.0003660578,0.00021814,0.001000124,0.000141881,0.0005451081,0.0005073597,0.0003147959,0.0001848318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124298,"about_ca_system_score_gemma":0.00004099541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370466,"about_ca_topic_score_gemma":0.000007909218,"domain_scores_codex":[0.9965224,0.00008051203,0.0008249875,0.0007760664,0.0007287619,0.001067249],"domain_scores_gemma":[0.9981993,0.0002369817,0.0002561439,0.0008885085,0.0001949238,0.0002240835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007351208,0.002061595,0.0001965222,0.0003669706,0.00005553727,0.0001293616,0.003186924,0.00005088414,0.0003186614,0.4235975,0.0005248816,0.5695038],"study_design_scores_gemma":[0.0007157003,0.0002765023,0.00004331862,0.0002531759,0.00004374983,0.0002932923,0.000243637,0.6696009,0.002126844,0.3176199,0.007945371,0.0008375375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004882547,0.00009593792,0.9937113,0.0004175416,0.0001261419,0.001171619,0.000003242319,0.002220098,0.001765857],"genre_scores_gemma":[0.02649548,9.882792e-7,0.9724559,0.0001172232,0.00006688287,0.0005120132,0.00002066662,0.00005440836,0.0002764528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6695501,"threshold_uncertainty_score":0.9998791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391019797","doi":"10.1109/mnet.2024.3355922","title":"(Com)<sup>2</sup>Net: A Novel Communication and Computation Integrated Network Architecture","year":2024,"lang":"en","type":"article","venue":"IEEE Network","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Calgary","funders":"National Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Cloud computing; Software deployment; Computation; The Internet; Distributed computing; Domain (mathematical analysis); Artificial intelligence; World Wide Web; Algorithm; Software engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01848259349535607,"gpt":0.2557321649710994,"spread":0.2372495714757433,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003790947,0.000235521,0.0002166808,0.0001325893,0.0002419553,0.0004977995,0.0006097934,0.0001361631,0.000004004135],"category_scores_gemma":[0.00002152032,0.0002190608,0.00005737507,0.001326732,0.0001067653,0.0002933081,0.0001940004,0.0004022807,0.00001191673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004848278,"about_ca_system_score_gemma":0.00005427208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001525178,"about_ca_topic_score_gemma":0.000005283731,"domain_scores_codex":[0.9984543,0.000130833,0.0003379173,0.0004796188,0.0002205807,0.0003768],"domain_scores_gemma":[0.9987166,0.0004745915,0.00008823444,0.0005386925,0.00007661248,0.0001052557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009687267,0.00002095428,0.00004958534,0.00001915814,0.00003548085,0.000003430029,0.0007717184,0.9200594,0.00001630448,0.0269995,0.02859921,0.02341554],"study_design_scores_gemma":[0.0001578841,0.00006902222,0.0001037608,0.0003274253,0.00001584747,0.00004853794,0.00001019445,0.9427366,0.00001815906,0.04711521,0.009176633,0.0002207567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007907997,0.002043085,0.9925401,0.001136324,0.001030746,0.0003974049,0.000004094665,0.00136451,0.0006929022],"genre_scores_gemma":[0.3606635,0.0001479745,0.6366579,0.0008412972,0.001244965,0.00009831322,0.00007409323,0.00005633273,0.000215669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3598727,"threshold_uncertainty_score":0.8933039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971055146","doi":"","title":"Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Jacobian matrix and determinant; Gradient descent; Maxima and minima; Parameterized complexity; Convergence (economics); Artificial neural network; Applied mathematics; Mathematics; Computer science; Mathematical optimization; Algorithm; Mathematical analysis; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03222558805984906,"gpt":0.1798108982464483,"spread":0.1475853101865993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001160574,0.0001565507,0.0002193454,0.0001438047,0.00005972925,0.00002845638,0.0008399122,0.00006280425,0.00002117215],"category_scores_gemma":[0.00002802358,0.0001676728,0.0001438989,0.0005820592,0.00007773385,0.0003814872,0.0002248721,0.0001000113,0.000005317826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007714796,"about_ca_system_score_gemma":0.00002536238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001739543,"about_ca_topic_score_gemma":0.00000225846,"domain_scores_codex":[0.9989135,0.00004145097,0.0001844094,0.0004929361,0.00007144838,0.0002962081],"domain_scores_gemma":[0.9988788,0.0001440426,0.0001911125,0.0005414121,0.0001552149,0.00008943759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001549685,0.0001176542,0.01121683,0.00004178064,0.00005275336,0.0000123827,0.0001633136,0.5006101,0.0009284229,0.4857311,0.0001850578,0.0007856544],"study_design_scores_gemma":[0.0007407904,0.0001949506,0.001450069,0.00001880557,0.00001455296,0.000002821483,0.00001720817,0.994463,0.000883524,0.002006943,0.00002493814,0.0001823937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3205087,0.00001601225,0.6783341,0.00001414745,0.0005830848,0.0003724842,0.000002816591,0.0001152522,0.00005350623],"genre_scores_gemma":[0.9857384,0.00001238055,0.01389382,0.00007407898,0.00001282523,0.000001674049,0.000005247383,0.000009492313,0.0002520929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6652297,"threshold_uncertainty_score":0.6837497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2782985982","doi":"10.1109/icmla.2017.0-166","title":"Anytime Exploitation of Stragglers in Synchronous Stochastic Gradient Descent","year":2017,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Descent (aeronautics); Stochastic gradient descent; Artificial intelligence; Engineering; Aerospace engineering; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.02369414696757149,"gpt":0.2663900930483598,"spread":0.2426959460807883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002111404,0.0001129629,0.0001621596,0.0002182215,0.0001036895,0.0001027158,0.0009386703,0.00004308442,0.00001850463],"category_scores_gemma":[0.0001830456,0.0001097418,0.00004056743,0.0001236357,0.00009265427,0.0005567284,0.0001770268,0.00006500135,0.000008163403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009347636,"about_ca_system_score_gemma":0.00005596312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167785,"about_ca_topic_score_gemma":0.00002184997,"domain_scores_codex":[0.9989508,0.00002228731,0.000294671,0.0002848787,0.0002341543,0.0002132323],"domain_scores_gemma":[0.9987499,0.00005475213,0.0002353017,0.0007975012,0.00009444455,0.00006815665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004131705,0.0008936588,0.00329684,0.00008402512,0.00004652836,0.00002837912,0.00572758,0.07740358,0.003418939,0.8374604,0.0005850156,0.07101373],"study_design_scores_gemma":[0.001046308,0.000422471,0.05784495,0.0001994985,0.000009533526,0.00001387113,0.000185168,0.9079193,0.009648311,0.02229045,0.000006708503,0.000413447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0285305,0.00001729805,0.9693071,0.0002262598,0.0001896783,0.0002995768,0.000001013709,0.0001282392,0.001300351],"genre_scores_gemma":[0.8380984,0.000003316313,0.1617887,0.00002103003,0.000007141605,0.00002650499,9.836714e-7,0.000006099217,0.00004781808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8305157,"threshold_uncertainty_score":0.4475139,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995434136","doi":"10.48550/arxiv.1905.12558","title":"Limitations of the Empirical Fisher Approximation for Natural Gradient\\n Descent","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Fisher information; Hessian matrix; Fisher kernel; Heuristics; Mathematics; Applied mathematics; Econometrics; Mathematical economics; Mathematical optimization; Statistics; Computer science; Artificial intelligence; Kernel method","retraction":null,"screen_n_in":null,"score":{"opus":0.2954199039827467,"gpt":0.2289787568300307,"spread":0.06644114715271598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004195444,0.0004788336,0.000519792,0.0003823271,0.0003597344,0.0001330623,0.002809469,0.0003811918,0.00001347173],"category_scores_gemma":[0.0005591364,0.00045375,0.0006982255,0.001470693,0.0003923696,0.0005394426,0.001684475,0.0005882217,0.00001696119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004926684,"about_ca_system_score_gemma":0.0004233898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000226636,"about_ca_topic_score_gemma":0.00001457673,"domain_scores_codex":[0.9969797,0.0002661499,0.00060647,0.001389274,0.0002514834,0.0005069967],"domain_scores_gemma":[0.9950235,0.0008445903,0.001045729,0.00192306,0.001025203,0.0001378795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000101143,0.0004695571,0.004628053,0.0002884351,0.0001929311,0.000002608863,0.002245918,0.6177351,0.00004979255,0.3710074,0.001620823,0.001658253],"study_design_scores_gemma":[0.000770342,0.0001497717,0.004289957,0.0002379312,0.0002099388,0.000003667512,0.0001617473,0.9582177,0.0005732715,0.03448184,0.0004477348,0.000456147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04539831,0.00004731787,0.9476411,0.0005301828,0.002581779,0.002875885,0.0000430706,0.0001482084,0.0007340957],"genre_scores_gemma":[0.9680316,0.0001060523,0.02976692,0.0001554862,0.00005056897,0.00001280301,0.00003702285,0.00003217711,0.001807396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9226332,"threshold_uncertainty_score":0.9997914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810910646","doi":"10.1016/j.neucom.2018.06.002","title":"Mini-batch algorithms with Barzilai–Borwein update step","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Stochastic gradient descent; Computer science; Sequence (biology); Algorithm; Regular polygon; Mathematical optimization; State (computer science); Stochastic optimization; Batch processing; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01115320935639728,"gpt":0.2379886590466911,"spread":0.2268354496902938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002328557,0.000228986,0.0001963381,0.0001767998,0.000283919,0.0002358702,0.001036743,0.00005742782,0.00001625935],"category_scores_gemma":[0.00004604556,0.0002039542,0.00004146666,0.0008210145,0.0001210509,0.0003095317,0.0004225102,0.0001746194,0.00009441825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966541,"about_ca_system_score_gemma":0.00006035281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001237063,"about_ca_topic_score_gemma":0.000001953736,"domain_scores_codex":[0.998086,0.0000692872,0.0002964099,0.0006865695,0.000391727,0.0004699618],"domain_scores_gemma":[0.9986659,0.0001210359,0.0001698903,0.0006593922,0.0002469826,0.0001368529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007975509,0.0004957139,0.004014513,0.0000892528,0.0001176574,0.0003736762,0.005006361,0.004873936,0.001838839,0.1819487,0.02274392,0.7784177],"study_design_scores_gemma":[0.0005756919,0.00063893,0.001234699,0.00006937099,0.000009195447,0.0001488356,0.00002211989,0.9831917,0.006967855,0.001114042,0.005604826,0.0004227291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008616522,0.00001199002,0.9861345,0.0006156045,0.000411622,0.0002871697,8.192511e-7,0.001155291,0.002766533],"genre_scores_gemma":[0.2488414,0.00000129244,0.7496477,0.001155387,0.0002494641,0.00001248894,0.000001816548,0.00002716121,0.00006326229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9783178,"threshold_uncertainty_score":0.8317012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963002787","doi":"","title":"Improved asynchronous parallel optimization analysis for stochastic incremental methods","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Asynchronous communication; Stochastic optimization; Mathematical optimization; Parallel computing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01686008516669065,"gpt":0.2740270218591956,"spread":0.257166936692505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004609542,0.0002505281,0.0003213476,0.0004699651,0.0005245807,0.0003967041,0.001444268,0.0001257102,0.00009232231],"category_scores_gemma":[0.001729412,0.0002682859,0.0002131102,0.00165775,0.0002341918,0.0004345624,0.0004915358,0.0001226064,0.000008049813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001413337,"about_ca_system_score_gemma":0.0001338305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001781898,"about_ca_topic_score_gemma":0.000159688,"domain_scores_codex":[0.9962234,0.001826712,0.0005086523,0.0007631632,0.000279516,0.0003984866],"domain_scores_gemma":[0.9940244,0.00139855,0.0004063378,0.001581475,0.002415344,0.0001739007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005526165,0.001092964,0.0004850387,0.00005442572,0.0009030165,0.000001147718,0.01236754,0.0626773,0.006837939,0.7886847,0.0006649961,0.1261757],"study_design_scores_gemma":[0.0005088542,0.000003465188,0.0001720859,0.00005049575,0.0001041555,0.000003790806,0.00002861668,0.9756498,0.02026375,0.002755255,0.0001851019,0.0002746511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003133751,0.0001009021,0.9938757,0.001526747,0.0001477012,0.0006814308,0.00001368779,0.0005752724,0.00276516],"genre_scores_gemma":[0.1681156,0.00001262179,0.8309131,0.0001191324,0.00002049476,0.0001695922,0.0001149303,0.00002347107,0.0005110353],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9129725,"threshold_uncertainty_score":0.9999769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894812324","doi":"10.1016/j.disopt.2023.100795","title":"Principled deep neural network training through linear programming","year":2023,"lang":"en","type":"article","venue":"Discrete Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Office of Naval Research; Institut de Valorisation des Données; National Science Foundation","keywords":"Computer science; Deep learning; Polyhedron; Artificial intelligence; Artificial neural network; Linear programming; Perspective (graphical); Dependency (UML); Task (project management); Representation (politics); Sample (material); Function (biology); Machine learning; Mathematical optimization; Algorithm; Theoretical computer science; Mathematics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.04017734624734458,"gpt":0.2895398856964629,"spread":0.2493625394491183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003378717,0.0002128354,0.0002051654,0.0001379996,0.0003138495,0.0002227489,0.000615901,0.00009880913,0.00001916953],"category_scores_gemma":[0.0001722186,0.0002119005,0.00008418348,0.002416539,0.00005187233,0.000908109,0.0002759902,0.0001361203,0.00002416529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004414388,"about_ca_system_score_gemma":0.00003597606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004824495,"about_ca_topic_score_gemma":0.000001781258,"domain_scores_codex":[0.998116,0.00007808072,0.0003756795,0.00051254,0.0003568407,0.0005609294],"domain_scores_gemma":[0.9990093,0.00008996257,0.0001831591,0.0004910667,0.000134621,0.00009184995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003862131,0.000008088374,0.00008195752,0.000007055783,0.00001048897,0.000005998399,0.001612352,0.955761,0.000003943111,0.03175353,0.00008937803,0.01066234],"study_design_scores_gemma":[0.0002319761,0.00007015122,0.00007238414,0.00002524846,0.00000911098,0.000007590823,0.0000997778,0.9972309,0.00003805693,0.001479221,0.0004936107,0.0002419125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001871664,0.00004300162,0.9942153,0.0005607739,0.0004408024,0.0005386477,0.000001395622,0.002790446,0.001222432],"genre_scores_gemma":[0.0510679,0.00003382201,0.9480601,0.0001942266,0.0001787391,0.0001478244,0.0001580378,0.0000407762,0.0001185773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05088073,"threshold_uncertainty_score":0.8641052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963114935","doi":"","title":"Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields","year":2015,"lang":"en","type":"article","venue":"ANU Open Research (Australian National University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Convergence (economics); Computer science; CRFS; Sampling (signal processing); Algorithm; Sampling scheme; Conditional random field; Stochastic gradient descent; Mathematical optimization; Rate of convergence; Mathematics; Artificial intelligence; Estimator; Statistics; Artificial neural network; Key (lock)","retraction":null,"screen_n_in":null,"score":{"opus":0.2458712651436055,"gpt":0.4074290261833877,"spread":0.1615577610397822,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028548,0.0001512217,0.0002169126,0.0007578349,0.0004379398,0.0003642613,0.002110354,0.0001182965,0.0000610423],"category_scores_gemma":[0.0006259034,0.0001671321,0.00008914406,0.001257656,0.0001362609,0.00133835,0.0005694763,0.0003051812,0.00002694411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004692533,"about_ca_system_score_gemma":0.001000065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001516527,"about_ca_topic_score_gemma":0.00002347586,"domain_scores_codex":[0.9975073,0.000178073,0.0002163892,0.0005200612,0.001084113,0.0004940429],"domain_scores_gemma":[0.9965829,0.000859487,0.00009567005,0.0002738305,0.001812876,0.0003751993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001688175,0.00009875879,0.00000705986,0.000009015572,0.00005466897,0.00002794707,0.00115856,0.03537354,0.00002136735,0.9012976,0.0609516,0.0008311236],"study_design_scores_gemma":[0.007988707,0.0007754628,0.00009450808,0.00007177379,0.00001598887,0.0000526293,0.001207766,0.5687389,0.0005718249,0.3782289,0.04173256,0.0005210064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001461747,0.000001524608,0.9790561,0.003658092,0.0001502292,0.001307726,0.00006608738,0.00007506645,0.01553899],"genre_scores_gemma":[0.3058046,0.000002594873,0.6582412,0.0002656909,0.000126163,0.0000788991,0.0002685181,0.00001963187,0.03519276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5333653,"threshold_uncertainty_score":0.6815449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894591993","doi":"10.1109/allerton.2018.8635903","title":"Anytime Stochastic Gradient Descent: A Time to Hear from all the Workers","year":2018,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Exploit; Computation; Convergence (economics); Node (physics); Distributed computing; Focus (optics); Acceleration; Algorithm; Artificial intelligence; Computer security; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01617655381045896,"gpt":0.2389224668351279,"spread":0.2227459130246689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002446552,0.0001902263,0.0001569668,0.0001307127,0.000181793,0.0002101065,0.001367882,0.00005314614,0.0006155111],"category_scores_gemma":[0.0001098468,0.000132649,0.00006325654,0.0006248078,0.0001257867,0.0001973467,0.0004641919,0.00009702584,0.003690452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000864831,"about_ca_system_score_gemma":0.00004505644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001561146,"about_ca_topic_score_gemma":0.00001022864,"domain_scores_codex":[0.9983991,0.00005860076,0.0002439043,0.0005169059,0.0003644166,0.0004170908],"domain_scores_gemma":[0.9984329,0.000173884,0.00006499777,0.0009654193,0.0001389831,0.0002238482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002031854,0.0008324484,0.0003188636,0.000009659587,0.0004608942,0.00002984888,0.0237719,0.01352679,0.005080279,0.143263,0.7517296,0.06077356],"study_design_scores_gemma":[0.0005347032,0.0008912885,0.001278908,0.0001081032,0.00003799214,0.00002333514,0.00008148056,0.9675542,0.00349057,0.01442274,0.01082319,0.0007535309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00167066,0.00001969074,0.9894232,0.004543613,0.0002605341,0.0005574867,0.0000039672,0.0007274958,0.002793333],"genre_scores_gemma":[0.3236048,8.193451e-7,0.6650056,0.007470044,0.000268402,0.0001149503,0.000007663199,0.00003746873,0.003490296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9540274,"threshold_uncertainty_score":0.9970853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196800830","doi":"10.1007/s10915-021-01628-3","title":"Stochastic Gradient Descent with Polyak’s Learning Rate","year":2021,"lang":"en","type":"article","venue":"Journal of Scientific Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Fundação para a Ciência e a Tecnologia; Institut de Valorisation des Données","keywords":"Stochastic gradient descent; Subgradient method; Mathematics; Constant (computer programming); Rate of convergence; Generalization; Gradient descent; Regular polygon; Descent (aeronautics); Applied mathematics; Convex function; Mathematical optimization; Convergence (economics); Artificial neural network; Mathematical analysis; Computer science; Artificial intelligence; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01466382442135339,"gpt":0.2337888838771633,"spread":0.21912505945581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001804826,0.0001687984,0.0002808562,0.0004244719,0.0005085673,0.0008903057,0.0007614308,0.00003688127,0.00001386229],"category_scores_gemma":[0.0004190676,0.0001398229,0.0001149388,0.001521757,0.0001350672,0.0004642846,0.0003271486,0.0003958033,0.000007046808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000136906,"about_ca_system_score_gemma":0.0004172618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001463931,"about_ca_topic_score_gemma":0.000001353479,"domain_scores_codex":[0.9977054,0.0001681873,0.0006029527,0.0004101444,0.0007170718,0.0003962372],"domain_scores_gemma":[0.9972362,0.0002425058,0.0007175788,0.0003643127,0.001227144,0.000212277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004928375,0.0005686044,0.002005008,0.00006880247,0.0002109595,0.0009354915,0.006671588,0.8514351,0.01463617,0.04176807,0.001825749,0.07982521],"study_design_scores_gemma":[0.001007627,0.0004543356,0.002243527,0.0007278178,0.00005313085,0.002451489,0.0003951102,0.9792116,0.01030387,0.001999127,0.0007245473,0.0004278625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08944787,0.000208353,0.9081093,0.0004125206,0.001493222,0.00007944539,2.759968e-7,0.0001033928,0.000145587],"genre_scores_gemma":[0.7990718,0.000001588211,0.2005634,0.00005527468,0.00008245339,5.283486e-7,0.000001027038,0.00001110551,0.00021272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.709624,"threshold_uncertainty_score":0.8585238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080910898","doi":"10.48550/arxiv.2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Simple (philosophy); Estimator; Probabilistic logic; Mathematical optimization; Applied mathematics; Mathematics; Computer science; Algorithm; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.07104277370489873,"gpt":0.2059147819171644,"spread":0.1348720082122656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001867014,0.0003809917,0.0004113404,0.000238181,0.0002151836,0.0002197609,0.001095862,0.0002495829,0.00001194884],"category_scores_gemma":[0.0002769517,0.000454079,0.0001481584,0.0004894558,0.0001497774,0.0003399786,0.001515699,0.0002912522,0.000004824624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001974838,"about_ca_system_score_gemma":0.0002108002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002082924,"about_ca_topic_score_gemma":0.000002041538,"domain_scores_codex":[0.997772,0.00006901158,0.0002907157,0.001408751,0.0001033276,0.0003561859],"domain_scores_gemma":[0.9981054,0.000210863,0.0003250238,0.0007858973,0.0002919876,0.0002808473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002475744,0.00004730148,0.00007432296,0.0001506682,0.00003589257,0.00002640688,0.0001738961,0.8009917,0.000005468867,0.1979834,0.0003556167,0.0001306484],"study_design_scores_gemma":[0.0005294637,0.0001856821,0.00003545922,0.00005590147,0.00008738264,0.000006408171,0.0000252308,0.9500002,0.00005148186,0.04852398,0.00006854226,0.0004302718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003550673,0.00003035305,0.9933858,0.0002904219,0.0002672056,0.001550142,0.00005508891,0.0007385836,0.0001317597],"genre_scores_gemma":[0.6014792,0.00003457444,0.3981582,0.000093975,0.0000418001,0.00002335157,0.00007630202,0.00002992264,0.00006275185],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5979285,"threshold_uncertainty_score":0.9997911,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2994062025","doi":"10.1109/tac.2020.3045094","title":"Continuous-Time Discounted Mirror Descent Dynamics in Monotone Concave Games","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Monotone polygon; Monotonic function; Regular polygon; Dynamics (music); Descent (aeronautics); Type (biology); Gradient descent; Legendre polynomials","retraction":null,"screen_n_in":null,"score":{"opus":0.0100666719676093,"gpt":0.2288216826494433,"spread":0.218755010681834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001740115,0.0002724473,0.0004710998,0.000238277,0.00009210688,0.0001355421,0.0006008779,0.0001018654,0.0001258021],"category_scores_gemma":[0.00004159986,0.0002701272,0.0001359986,0.0005914861,0.00007982102,0.0003249004,0.000003894711,0.0002086642,0.0001388874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003282737,"about_ca_system_score_gemma":0.0000908654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005132822,"about_ca_topic_score_gemma":0.00003674269,"domain_scores_codex":[0.9980992,0.0001239135,0.0005785719,0.000478845,0.000357935,0.0003615447],"domain_scores_gemma":[0.9987997,0.0003115091,0.0001629763,0.0004488195,0.00009050515,0.0001865349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001053925,0.00797923,0.0009567678,0.0007758521,0.00176173,0.0006203622,0.026042,0.2100587,0.03270875,0.0653368,0.002261684,0.6504441],"study_design_scores_gemma":[0.002054017,0.0002587492,0.0001854135,0.00007743204,0.00003259122,0.000008975537,0.00007807097,0.9946838,0.002072254,0.0002664517,0.00001769663,0.0002645213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00558674,0.00001461665,0.9871432,0.004517699,0.0002094056,0.001145572,0.00003893606,0.001156767,0.0001871129],"genre_scores_gemma":[0.9624148,0.000004806566,0.03591774,0.001291519,0.000007993436,0.0002461317,0.000002880947,0.00002601278,0.00008812453],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9568281,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3171596153","doi":"10.1109/jsac.2021.3087272","title":"LOSP: Overlap Synchronization Parallel With Local Compensation for Fast Distributed Training","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Research Grants Council, University Grants Committee; China Postdoctoral Science Foundation; Impact Fund; Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Synchronization (alternating current); Computation; Speedup; Distributed computing; Overhead (engineering); Convergence (economics); Stochastic gradient descent; Rate of convergence; Compensation (psychology); Data synchronization; Mathematical optimization; Parallel computing; Algorithm; Key (lock); Computer network; Artificial intelligence; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.03917666790837083,"gpt":0.2856775653390298,"spread":0.246500897430659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003112482,0.000173023,0.0002340419,0.0002478045,0.0004662334,0.0002590248,0.001084053,0.00008993105,0.000007930944],"category_scores_gemma":[0.0003214473,0.0001678626,0.00005290133,0.001690856,0.00009852886,0.000447622,0.00008461929,0.0004569,0.000003302319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004067324,"about_ca_system_score_gemma":0.0005720269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000458572,"about_ca_topic_score_gemma":0.00008633645,"domain_scores_codex":[0.9983737,0.0002635555,0.0004855109,0.000266795,0.000320174,0.000290289],"domain_scores_gemma":[0.996714,0.0006320817,0.0003110323,0.0009732004,0.001257835,0.0001118681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001654565,0.001529207,0.002775835,0.00003165619,0.0002115296,0.00004130507,0.00364333,0.6034523,0.0006457759,0.3254565,0.002215389,0.05983171],"study_design_scores_gemma":[0.001540602,0.0003153134,0.00333842,0.0003063427,0.00002416334,0.0003910182,0.0002974968,0.9854295,0.0007112382,0.006544999,0.0007999973,0.000300925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001079609,0.0000879177,0.9952255,0.002631913,0.0001225191,0.0003316126,0.00002048382,0.0001789216,0.0003214924],"genre_scores_gemma":[0.6904431,0.00008722878,0.3089691,0.0001832148,0.00003111215,0.00006973521,0.0001819175,0.00001627365,0.00001825231],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6893635,"threshold_uncertainty_score":0.6845239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036623140","doi":"10.1007/s10957-023-02297-y","title":"Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization","year":2023,"lang":"en","type":"article","venue":"Journal of Optimization Theory and Applications","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Global Collaborative Research, King Abdullah University of Science and Technology; Institut de Valorisation des Données; King Abdullah University of Science and Technology","keywords":"Mathematics; Convexity; Stochastic gradient descent; Convex function; Theory of computation; Convergence (economics); Mathematical optimization; Convex optimization; Applied mathematics; Variance (accounting); Regular polygon; Algorithm; Computer science; Artificial intelligence; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01997888666737985,"gpt":0.3296915564201645,"spread":0.3097126697527846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001651971,0.0001257511,0.0003623411,0.001050771,0.0001798808,0.00007560514,0.0002927536,0.00006616234,0.000008030246],"category_scores_gemma":[0.0002200752,0.0001169905,0.0001029334,0.002221515,0.0001240968,0.0002982793,0.00007895998,0.00007194743,1.570127e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002118543,"about_ca_system_score_gemma":0.00003955265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.418002e-7,"about_ca_topic_score_gemma":8.722086e-8,"domain_scores_codex":[0.9987174,0.0001880223,0.0006024913,0.0002188544,0.0001421997,0.0001309816],"domain_scores_gemma":[0.9971714,0.001189097,0.0007067976,0.0002515015,0.0005754941,0.0001056926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002278202,0.0000334548,0.00001420335,0.00001298087,0.0001519054,9.528527e-8,0.0002511229,0.721257,0.0001326533,0.273998,0.00001295629,0.004112837],"study_design_scores_gemma":[0.0003562534,0.0001005856,0.0001392292,0.00001804189,0.0004541283,0.000007966722,0.00009103995,0.9735177,0.000269915,0.02489204,0.00004550619,0.000107551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001828173,0.0001695917,0.9987539,0.0002288826,0.00005432805,0.0004778955,0.00001386893,0.00007790751,0.00004081464],"genre_scores_gemma":[0.04205905,0.0001877958,0.9574853,0.00006694868,0.00002238402,0.00008816701,0.00004231723,0.00001293836,0.00003507991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2522607,"threshold_uncertainty_score":0.4770735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896830491","doi":"10.1287/ijoo.2022.0072","title":"A Subsampling Line-Search Method with Second-Order Results","year":2022,"lang":"en","type":"article","venue":"INFORMS Journal on Optimization","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Agence Nationale de la Recherche","keywords":"Line search; Computer science; Context (archaeology); Mathematical optimization; Function (biology); Sample (material); Line (geometry); Saddle point; Reduction (mathematics); Algorithm; Artificial intelligence; Mathematics; Path (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.02840894031896267,"gpt":0.2941041273880469,"spread":0.2656951870690842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001478566,0.0001835239,0.0001833371,0.000672436,0.0007438437,0.0004257454,0.0008455968,0.00004976045,0.0002389446],"category_scores_gemma":[0.000175012,0.0001465406,0.00005727664,0.001472517,0.00002516033,0.001069202,0.0002477413,0.0006510774,0.000006542438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002508575,"about_ca_system_score_gemma":0.0002716569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004303354,"about_ca_topic_score_gemma":8.52484e-7,"domain_scores_codex":[0.9977881,0.0001055896,0.0005658838,0.0002913955,0.0009079797,0.0003410508],"domain_scores_gemma":[0.9983073,0.0001901454,0.0003984048,0.0004215915,0.0005292628,0.0001532687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001482075,0.00005033171,0.00001083179,0.000003166425,0.00001910443,0.00001554879,0.0009021129,0.9819834,0.000007081179,0.01086562,0.0003429713,0.005651662],"study_design_scores_gemma":[0.001138651,0.001159775,0.00001543951,0.00002352907,0.000005606921,0.0005809899,0.0001285423,0.9935711,0.0004936891,0.0006326585,0.002027291,0.0002227537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000261262,0.00001416234,0.9943375,0.0008951443,0.0002943017,0.0002802928,0.00001009669,0.0002488511,0.003658365],"genre_scores_gemma":[0.0145698,0.00001840719,0.983784,0.000922017,0.00006824269,0.00004092287,0.00002982192,0.00002496002,0.0005418668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01430854,"threshold_uncertainty_score":0.5975752,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}