{"id":"W2163187564","doi":"10.48550/arxiv.1503.08329","title":"Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian probability; Statistical learning theory; Computer science; Upper and lower bounds; Divergence (linguistics); AdaBoost; Artificial intelligence; Probably approximately correct learning; Machine learning; Algorithm; Bayesian statistics; Mathematics; Support vector machine; Bayesian inference; Algorithmic learning theory; Unsupervised learning","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":[0.0007455516,0.0001935214,0.0002556866,0.0002428337,0.0005496698,0.0002383727,0.00122427,0.0000799953,0.00001115831],"category_scores_gemma":[0.0002338043,0.0001659447,0.0002582805,0.002231292,0.0000548117,0.0002943964,0.000358858,0.0003804764,0.00005127529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001036576,"about_ca_system_score_gemma":0.00008577864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004776123,"about_ca_topic_score_gemma":0.0004441171,"domain_scores_codex":[0.9983518,0.0002589658,0.0001426781,0.0007255552,0.0001402873,0.0003807715],"domain_scores_gemma":[0.9981632,0.0004346385,0.0001479093,0.0007554163,0.0001723905,0.0003264081],"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":[0.00007899753,0.0001454938,0.08702463,0.000004939442,0.001532246,0.0001303796,0.003621144,0.7516295,0.000008635026,0.01586757,0.001703489,0.138253],"study_design_scores_gemma":[0.0005359821,0.0001361471,0.006244583,0.000003501857,0.0003644039,0.000001092006,0.0003124152,0.9752886,0.00001180344,0.006463458,0.01040372,0.0002343014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03887625,0.0000475248,0.9596604,0.0004675833,0.0002446683,0.0001723397,0.00002556172,0.0002206978,0.0002850433],"genre_scores_gemma":[0.9522291,0.000011423,0.04481906,0.0001479024,0.0001755761,0.000001384498,0.00001284845,0.00001182658,0.002590907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9148413,"threshold_uncertainty_score":0.7220102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03610584429556141,"score_gpt":0.1980005763968624,"score_spread":0.161894732101301,"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."}}