{"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,"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","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07104277370489873,"score_gpt":0.2059147819171644,"score_spread":0.1348720082122656,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}