{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001495746,0.0001174707,0.00009028044,0.0002339667,0.0002775456,0.0003745242,0.0007106547,0.00003993314,0.0003265864],"category_scores_gemma":[0.000127414,0.0001051628,0.0000349432,0.0002595771,0.00009802163,0.0003720422,0.0001360035,0.0002110862,0.0002766325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003771685,"about_ca_system_score_gemma":0.00006699921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002549666,"about_ca_topic_score_gemma":0.000007007877,"domain_scores_codex":[0.9988049,0.00007712637,0.0001908236,0.0003924841,0.0003631311,0.0001715864],"domain_scores_gemma":[0.9989278,0.000116222,0.0001409855,0.000292481,0.0004641078,0.00005846056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001193856,0.0002769679,0.04918191,0.000008984355,0.000227355,0.00006790343,0.01006991,0.02024417,0.003031957,0.8518962,0.01908701,0.04578825],"study_design_scores_gemma":[0.0005864131,0.0005294085,0.0124647,0.0001400278,0.000007353925,0.00005131841,0.000228669,0.962369,0.00517142,0.005702202,0.01234207,0.0004074706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0145914,0.000001978538,0.8108089,0.005079582,0.0002584369,0.00008709991,0.000001150149,0.0004598781,0.1687116],"genre_scores_gemma":[0.9153085,0.000005910161,0.0785519,0.0004140075,0.0001522076,0.00002087537,0.00001417453,0.000009171077,0.005523214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9421248,"threshold_uncertainty_score":0.4288416,"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."}}