{"id":"W2904014149","doi":"","title":"Finding Flatter Minima with SGD","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Maxima and minima; Computer science; Artificial intelligence; Mathematics; Mathematical analysis","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":[0.002336433,0.002298079,0.002956741,0.002389768,0.00103821,0.002068,0.001809753,0.002995811,0.0146362],"category_scores_gemma":[0.0102901,0.001667268,0.001606715,0.001542679,0.001441751,0.002770636,0.002986094,0.003308178,0.003071231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025726,"about_ca_system_score_gemma":0.001604368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002783182,"about_ca_topic_score_gemma":0.004545108,"domain_scores_codex":[0.9990085,0.0003420722,0.0000777255,0.0002526786,0.0002150973,0.000103944],"domain_scores_gemma":[0.9975498,0.001561311,0.0001345495,0.0003648995,0.0002665409,0.0001230048],"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":[0.0006436342,0.0002504713,0.001373687,0.0003514887,0.0001953979,0.0002375761,0.0002272107,0.5764237,0.005313766,0.04689321,0.01882637,0.3492635],"study_design_scores_gemma":[0.00007117677,0.00006738495,0.0001206312,0.00002530177,0.00001650502,0.0000326065,0.00003064722,0.9612436,0.0009239032,0.0363182,0.001138879,0.0000111812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02137474,0.0004456179,0.9703159,0.0004148908,0.0001502976,0.00008610493,0.0001345731,0.00245077,0.004627147],"genre_scores_gemma":[0.2197748,0.000185264,0.7699496,0.0005385891,0.00009981955,0.0002804007,0.000652539,0.001971717,0.006547383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0146362,"threshold_uncertainty_score":0.04896295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0514478710076336,"score_gpt":0.3483785570925074,"score_spread":0.2969306860848738,"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."}}