{"id":"W3212182603","doi":"","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks.","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pruning; Artificial neural network; Computer science; Generalization; Compressibility; Limit (mathematics); Compression (physics); Node (physics); Computation; Mathematics; Algorithm; Mathematical optimization; Applied mathematics; Artificial intelligence; Mathematical analysis; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002324359,0.0001382707,0.0002663433,0.0001552466,0.00009457031,0.0001676197,0.0006854949,0.00008267616,0.00002150989],"category_scores_gemma":[0.001652721,0.0001506193,0.00006341671,0.001096127,0.0001728485,0.00029002,0.0006453624,0.0001832687,8.440202e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004335082,"about_ca_system_score_gemma":0.0000787589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002417452,"about_ca_topic_score_gemma":0.0002446934,"domain_scores_codex":[0.9964541,0.00212554,0.0004380002,0.0005044258,0.0002486796,0.0002292427],"domain_scores_gemma":[0.9958538,0.001560784,0.0002242833,0.001273454,0.0009849925,0.0001026373],"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":[0.00003840718,0.001666775,0.03793983,0.000134902,0.00004909778,0.00002436976,0.009492728,0.004908505,0.005368084,0.8362147,0.0005109567,0.1036517],"study_design_scores_gemma":[0.0006206428,7.06136e-7,0.01529594,0.0002309295,0.000005121452,0.00001426885,0.00003263262,0.9342936,0.04374018,0.005473366,0.0001225944,0.0001699783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09488213,0.000976786,0.8995663,0.001817758,0.00006867569,0.0001905071,0.000003856576,0.0001363177,0.002357654],"genre_scores_gemma":[0.7796637,0.0001146558,0.2199597,0.00006724554,0.00000259573,0.00001401166,0.00001587241,0.000007684781,0.0001545019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9293851,"threshold_uncertainty_score":0.6142076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208512051257982,"score_gpt":0.226041951742967,"score_spread":0.2139568312303872,"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."}}