{"id":"W4387294078","doi":"10.48550/arxiv.2309.17016","title":"Efficient Agnostic Learning with Average Smoothness","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Ben-Gurion University of the Negev","keywords":"Smoothness; Bounded function; Nonparametric statistics; Mathematics; Rate of convergence; Uniform convergence; Applied mathematics; Algorithm; Monotonic function; Computer science; Entropy (arrow of time); Uniform boundedness; Cross entropy; Metric (unit); Discrete mathematics; Mathematical optimization; Artificial intelligence; Mathematical analysis; Statistics; Principle of maximum entropy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035732,0.0003752974,0.0003536847,0.0003439157,0.0003345623,0.0002151312,0.001679568,0.0002001519,0.00002385921],"category_scores_gemma":[0.0001000018,0.0003729495,0.0001524885,0.0009197826,0.00009467375,0.00007917488,0.002114882,0.001434474,0.0004049441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128036,"about_ca_system_score_gemma":0.0001799638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000326161,"about_ca_topic_score_gemma":0.00002050477,"domain_scores_codex":[0.9975632,0.0002443402,0.0001652271,0.001357302,0.0001793012,0.0004905764],"domain_scores_gemma":[0.9981171,0.0003003344,0.0002469973,0.001016369,0.000126788,0.0001923866],"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":[0.00001059466,0.00004718354,0.003700882,0.0000654219,0.00005207645,0.001185857,0.000308489,0.9799148,0.00000267786,0.01390832,0.00004759603,0.0007561131],"study_design_scores_gemma":[0.0003981961,0.00009435317,0.003627707,0.000212949,0.00003805626,0.000009731143,0.00004150267,0.9925622,0.00001244187,0.002075013,0.0004279253,0.000499905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2701494,0.00002090185,0.7265133,0.0001353344,0.0005915746,0.0001703843,0.000003261821,0.0009923322,0.001423578],"genre_scores_gemma":[0.9881499,0.00002864559,0.001665461,0.00003830422,0.0001013497,0.000001440615,0.00001589445,0.00004017348,0.009958836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7248478,"threshold_uncertainty_score":0.9998723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04398183531366383,"score_gpt":0.1837970187014434,"score_spread":0.1398151833877796,"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."}}