{"id":"W2547508527","doi":"10.48550/arxiv.1605.01288","title":"Fast rates with high probability in exp-concave statistical learning","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics; Empirical risk minimization; Bounded function; Lipschitz continuity; Upper and lower bounds; Regret; Combinatorics; Exponential function; Discrete mathematics; Applied mathematics; Mathematical optimization; Statistics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004266371,0.0003350034,0.000403625,0.0002037608,0.0001327782,0.000135646,0.00112992,0.0001986156,0.00006587803],"category_scores_gemma":[0.0001102237,0.000279735,0.00006918326,0.0003825268,0.0001885668,0.0002663033,0.001257295,0.001174603,0.00007901517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002201231,"about_ca_system_score_gemma":0.0002449686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005002501,"about_ca_topic_score_gemma":0.00008882584,"domain_scores_codex":[0.9974293,0.0004751885,0.000211461,0.001305305,0.0001276561,0.0004510984],"domain_scores_gemma":[0.998373,0.0003432869,0.0002128157,0.0007845993,0.0001165447,0.0001697038],"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":[0.000104606,0.000213265,0.1118289,0.0001930201,0.00008531796,0.001243651,0.0008762081,0.4383335,0.00001849273,0.4367702,0.00006895886,0.01026386],"study_design_scores_gemma":[0.001488486,0.0003105409,0.03718966,0.0003871479,0.00003256774,0.00001146985,0.000108462,0.794953,0.00008843811,0.164289,0.0002235275,0.0009177843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3285798,0.000009244632,0.6692339,0.0001590883,0.0001612766,0.0002028892,0.000009192327,0.0002053577,0.001439317],"genre_scores_gemma":[0.9876244,0.00001396437,0.01028866,0.00002578886,0.000064881,0.000002152607,0.00001418805,0.00001752167,0.001948404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6590446,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03396108820979779,"score_gpt":0.1897200050570574,"score_spread":0.1557589168472596,"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."}}