{"id":"W2182286517","doi":"","title":"From PAC-Bayes Bounds to Quadratic Programs for Majority Votes","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Margin (machine learning); Upper and lower bounds; AdaBoost; Bayes' theorem; Mathematics; Quadratic equation; Divergence (linguistics); Minification; Basis (linear algebra); Combinatorics; Computer science; Algorithm; Support vector machine; Mathematical optimization; Artificial intelligence; Machine learning; Bayesian probability","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":[0.0101115,0.002039227,0.002124246,0.001514971,0.001262892,0.00484926,0.003210419,0.002967817,0.007245364],"category_scores_gemma":[0.03875239,0.001336894,0.001179626,0.001443334,0.003869014,0.007734678,0.00529374,0.00722722,0.001564558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002975956,"about_ca_system_score_gemma":0.002603913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002218257,"about_ca_topic_score_gemma":0.002035938,"domain_scores_codex":[0.9930986,0.003218484,0.0001865273,0.0009781136,0.002035213,0.0004831257],"domain_scores_gemma":[0.9830059,0.01307651,0.0007584596,0.0009758834,0.001777894,0.0004053683],"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":[0.0001102339,0.00007755385,0.0004490569,0.0001767372,0.00005491619,0.00005456756,0.0001988971,0.2428363,0.0005501755,0.6747662,0.006242676,0.07448282],"study_design_scores_gemma":[0.00001307852,0.00001909214,0.00005148109,0.00004261693,0.000007705136,0.00001645343,0.00001538784,0.6551448,0.0004535352,0.3420186,0.002205621,0.00001164138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001764212,0.0004570856,0.9926246,0.0004797828,0.00005567443,0.00002794901,0.00002739165,0.000106732,0.004456534],"genre_scores_gemma":[0.284379,0.001643895,0.6925526,0.001461689,0.0009500215,0.0007593217,0.0003903412,0.001059808,0.01680327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0101115,"threshold_uncertainty_score":0.05347532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06972141086261915,"score_gpt":0.3134253480200855,"score_spread":0.2437039371574663,"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."}}