{"id":"W2155894447","doi":"10.48550/arxiv.1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":292,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kronecker delta; Curvature; Stochastic gradient descent; Hessian matrix; Diagonal; Gradient descent; Artificial neural network; Mathematics; Matrix (chemical analysis); Invertible matrix; Applied mathematics; Rank (graph theory); Mathematical optimization; Algorithm; Computer science; Combinatorics; Geometry; Pure mathematics; Artificial intelligence; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001218089,0.001037576,0.000916725,0.0005756362,0.0003781051,0.0009505406,0.001174228,0.001307273,0.001465494],"category_scores_gemma":[0.006036743,0.000652867,0.0006598686,0.0005840303,0.001003218,0.001801206,0.001257897,0.001202942,0.0006059836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001228203,"about_ca_system_score_gemma":0.001484532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007196387,"about_ca_topic_score_gemma":0.008855534,"domain_scores_codex":[0.9994763,0.0001660992,0.0000310646,0.000104226,0.0001633527,0.00005900031],"domain_scores_gemma":[0.9988508,0.0004759577,0.0001345812,0.0002094199,0.0002711012,0.00005816573],"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":[0.00005361523,0.00002362687,0.000558262,0.00004466522,0.00003421003,0.00003640692,0.00004227318,0.943401,0.00249762,0.01572659,0.001060856,0.03652083],"study_design_scores_gemma":[0.000002324568,0.000007928885,0.00003693914,0.000002213155,0.000001378951,0.000006537411,0.000001919965,0.9962315,0.0002588563,0.003283869,0.0001638817,0.000002627845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01690152,0.0001872338,0.9812228,0.0001486177,0.00003262588,0.00002181777,0.00003998084,0.0004888009,0.0009565179],"genre_scores_gemma":[0.5157895,0.000317256,0.4788544,0.0002069519,0.00006867534,0.0001455797,0.000322842,0.0002876159,0.00400715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007196387,"threshold_uncertainty_score":0.01430899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06471831599879245,"score_gpt":0.1881355193432239,"score_spread":0.1234172033444314,"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."}}