{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003967402,0.0002547241,0.0002322114,0.000189253,0.0002663249,0.0004973503,0.001316017,0.00007458041,0.0003608845],"category_scores_gemma":[0.0004147675,0.0002295368,0.0001168021,0.0001799638,0.00003725841,0.0003136933,0.000244499,0.0005040612,0.0002128797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005053839,"about_ca_system_score_gemma":0.00006611843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002250555,"about_ca_topic_score_gemma":0.0001344706,"domain_scores_codex":[0.9981223,0.0001341149,0.000310011,0.0006408662,0.0004492788,0.0003434526],"domain_scores_gemma":[0.9988821,0.0001827195,0.0001705577,0.0003363873,0.0002572632,0.0001709622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000173021,0.0004078175,0.03892098,0.00002153853,0.0001782053,0.00003063926,0.008586193,0.000525916,0.000992944,0.331547,0.000374139,0.6182417],"study_design_scores_gemma":[0.0007776839,0.001010285,0.008348304,0.000151283,0.00001345871,0.000008487855,0.0001914756,0.9140614,0.0007030532,0.05402113,0.02016057,0.0005528086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05630509,0.00003478727,0.9169764,0.005460813,0.001453082,0.0004094567,0.00002795874,0.0005904781,0.01874196],"genre_scores_gemma":[0.8879699,0.000004098717,0.109022,0.0003937655,0.0003454701,0.00009038131,0.00009203155,0.00002039106,0.00206194],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9135355,"threshold_uncertainty_score":0.936024,"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."}}