{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01196447,0.002532731,0.002372519,0.001518447,0.001126997,0.003521438,0.005341138,0.002841569,0.006582958],"category_scores_gemma":[0.05262321,0.001359275,0.002159621,0.002094268,0.00386956,0.007560027,0.008741491,0.008597557,0.003273441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002974818,"about_ca_system_score_gemma":0.002615328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002082529,"about_ca_topic_score_gemma":0.002373416,"domain_scores_codex":[0.9929485,0.002862305,0.0003408343,0.001163303,0.002081649,0.0006034261],"domain_scores_gemma":[0.9745867,0.0180007,0.0009721521,0.004159044,0.001556411,0.0007248762],"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":[0.0007097374,0.0003674748,0.002562965,0.0004551998,0.0001231364,0.0003900125,0.0005477489,0.3542437,0.00575032,0.4382675,0.01115987,0.1854223],"study_design_scores_gemma":[0.00005775575,0.00007937046,0.0002403749,0.00003915433,0.0000198134,0.0001175389,0.00002573138,0.8472311,0.002394795,0.1477384,0.002030758,0.00002514876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004917311,0.0002889448,0.9910964,0.0006196768,0.00005447711,0.00008367839,0.00005545999,0.0007357528,0.00214839],"genre_scores_gemma":[0.2536945,0.0008800253,0.7289936,0.001372255,0.0004605759,0.0009675464,0.0005274852,0.001049883,0.0120541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01196447,"threshold_uncertainty_score":0.06327492,"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."}}