{"id":"W2098000447","doi":"10.7551/mitpress/7503.003.0061","title":"A PAC-Bayes Risk Bound for General Loss Functions","year":2007,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Upper and lower bounds; Bayes' theorem; Set (abstract data type); Bayesian probability; Mathematics; AdaBoost; Exponential function; Statistics; Computer science; Artificial intelligence; Mathematical analysis; Classifier (UML)","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":[0.0005758732,0.0003712355,0.0003113381,0.00009613223,0.0006116894,0.0003266931,0.001241935,0.0002312797,0.00002359735],"category_scores_gemma":[0.00002647034,0.0002618022,0.0003095329,0.000009146101,0.0001791753,0.00005596871,0.0003633801,0.0007510784,0.00005165162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003396562,"about_ca_system_score_gemma":0.00006632014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003656928,"about_ca_topic_score_gemma":0.00005364209,"domain_scores_codex":[0.9983269,0.0000558274,0.0003094821,0.0005560362,0.0003370974,0.0004146319],"domain_scores_gemma":[0.9980389,0.0003103582,0.0003042498,0.001127977,0.0001110516,0.0001074208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002487753,0.00001178654,0.000003006109,0.00003769367,0.0002478291,0.00001728137,0.0006367408,0.0001746911,0.000006143795,0.7270735,0.008255498,0.263511],"study_design_scores_gemma":[0.0002923435,0.0001042947,0.0000106765,0.00004976882,0.0001210849,0.00003110318,0.000001511817,0.01592552,0.00005878801,0.05545582,0.9275905,0.0003585928],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00003179523,0.0008135486,0.4037102,0.0001013625,0.0009130489,0.0004523674,0.00008705632,0.0002613342,0.5936293],"genre_scores_gemma":[0.0002854445,0.00003143667,0.01043123,0.0002487298,0.001511109,0.00006221468,0.00001698552,0.00005979495,0.987353],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.919335,"threshold_uncertainty_score":0.9999834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03722296304277321,"score_gpt":0.2710257294086874,"score_spread":0.2338027663659141,"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."}}