{"id":"W4387838993","doi":"10.48550/arxiv.2310.12771","title":"Stochastic Average Gradient : A Simple Empirical Investigation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Université de Montréal; Compute Canada","keywords":"Rate of convergence; Convergence (economics); Mathematical optimization; Computer science; Simple (philosophy); Artificial neural network; Convex function; Gradient method; Function (biology); Stochastic approximation; Mathematics; Algorithm; Applied mathematics; Regular polygon; Artificial intelligence; Key (lock)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003265582,0.0003991866,0.0003700583,0.0006591471,0.0002047543,0.0001795292,0.001903404,0.0003347912,0.00001882516],"category_scores_gemma":[0.0002143715,0.0004812339,0.0002124877,0.001326281,0.0001630416,0.0003379715,0.002564994,0.0005969949,0.0001747526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004124,"about_ca_system_score_gemma":0.0002791768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001098835,"about_ca_topic_score_gemma":0.00002434159,"domain_scores_codex":[0.9973774,0.0001635193,0.0003250941,0.001466064,0.0001984887,0.0004694132],"domain_scores_gemma":[0.9974177,0.0002546951,0.0003252011,0.001463756,0.0002285964,0.0003099822],"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":[0.000007312159,0.00004563365,0.0009913594,0.00003911097,0.0000476426,0.0001257627,0.0005688835,0.860387,0.000007510837,0.1354655,0.002216882,0.00009735926],"study_design_scores_gemma":[0.0001917245,0.00005391429,0.0009882395,0.00006232333,0.00003018682,0.000004036901,0.0000180697,0.7133234,0.00004007539,0.2848944,0.00003552969,0.0003581648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04677475,0.00001094846,0.9494206,0.000314979,0.000714164,0.0005739557,0.00002191976,0.001981847,0.0001867813],"genre_scores_gemma":[0.9891025,0.00001744458,0.009691651,0.0001966641,0.00006737438,0.000009191525,0.00008061089,0.00004068395,0.0007939099],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9423277,"threshold_uncertainty_score":0.9997639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1405757196807451,"score_gpt":0.2286035112568162,"score_spread":0.0880277915760711,"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."}}