{"id":"W3212707937","doi":"","title":"On Empirical Risk Minimization with Dependent and Heavy-Tailed Data","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Empirical risk minimization; Independent and identically distributed random variables; Heavy-tailed distribution; Minification; Multiplier (economics); Mixing (physics); Computer science; Mathematics; Applied mathematics; Econometrics; Mathematical optimization; Statistical physics; Statistics; Random variable; 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":[0.0003541155,0.0001270318,0.0002045981,0.00005112731,0.0001760946,0.0004196269,0.0001208334,0.00006638059,0.00001653218],"category_scores_gemma":[0.002050167,0.00008969393,0.000009001696,0.0001809301,0.00002853713,0.0008784842,0.00006863523,0.0001597494,0.00001000737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002431384,"about_ca_system_score_gemma":0.00008944558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001046259,"about_ca_topic_score_gemma":0.00000513749,"domain_scores_codex":[0.9987207,0.0001605398,0.0004427569,0.0001805824,0.0003477703,0.0001476364],"domain_scores_gemma":[0.9985067,0.0005140588,0.0003079796,0.0003244396,0.0002689765,0.00007783623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001391796,0.0005960966,0.02995165,0.009782941,0.0002017219,0.00007393539,0.01140516,0.005167222,0.0001127327,0.1472185,0.02184741,0.7722508],"study_design_scores_gemma":[0.001121455,0.0002354612,0.001749828,0.0005530402,0.00008682967,0.0001968837,0.001412177,0.9833797,0.0003521827,0.008967145,0.001592046,0.0003533118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1760796,0.0001357815,0.8197831,0.0003247536,0.0002444774,0.0003570844,0.0001320246,0.0001485426,0.002794615],"genre_scores_gemma":[0.9583613,0.00001161737,0.04110335,0.0002663168,0.00005267933,0.0000204948,0.00009653041,0.0000114736,0.00007627631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9782124,"threshold_uncertainty_score":0.4046471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1348890363222765,"score_gpt":0.3872739073271205,"score_spread":0.252384871004844,"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."}}