{"id":"W3196987049","doi":"10.48550/arxiv.2109.02224","title":"On Empirical Risk Minimization with Dependent and Heavy-Tailed Data","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"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; Mixing (physics); Econometrics; Multiplier (economics); Mathematics; Applied mathematics; Convergence (economics); Regression; Statistical physics; Computer science; Mathematical optimization; Statistics; Economics; Physics; Random variable","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":[0.0003000115,0.0002525329,0.0003901652,0.00008340722,0.0001061229,0.00008631134,0.000449822,0.0002243701,0.0001843084],"category_scores_gemma":[0.001405798,0.0002277123,0.00003772906,0.0001760149,0.0001123381,0.00008257142,0.001130795,0.0005678514,0.0000078329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000699998,"about_ca_system_score_gemma":0.0001457665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006805598,"about_ca_topic_score_gemma":0.0001564044,"domain_scores_codex":[0.9981201,0.000385547,0.0001826292,0.0009971285,0.0001141232,0.0002004383],"domain_scores_gemma":[0.9967731,0.001454333,0.0002235683,0.001264829,0.0001305341,0.0001536329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002427109,0.001803508,0.1077245,0.00141432,0.001241862,0.002564173,0.001232774,0.02494221,0.00001042723,0.843362,0.004255751,0.009021355],"study_design_scores_gemma":[0.001521233,0.0003387311,0.008549351,0.0005647555,0.0009811159,0.00001404308,0.0005476115,0.3736633,0.00007641174,0.612785,0.00009788178,0.0008605177],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4260207,0.00001549118,0.5725561,0.00002937042,0.00007638797,0.0001711832,0.0001731862,0.000042859,0.0009147435],"genre_scores_gemma":[0.9254736,0.0002080379,0.07381504,0.00005773086,0.00003515535,7.356825e-7,0.0001002406,0.00002453164,0.0002849463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4994529,"threshold_uncertainty_score":0.9285837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2918614297256289,"score_gpt":0.3004399801184141,"score_spread":0.008578550392785211,"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."}}