{"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,"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","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":["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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08007162583441403,"score_gpt":0.3591140077257221,"score_spread":0.279042381891308,"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."}}