{"id":"W3173332884","doi":"10.48550/arxiv.2106.12535","title":"Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Generalization; Prior probability; Differentiable function; Computer science; Bayes' theorem; Series (stratigraphy); Artificial intelligence; Dirichlet distribution; Upper and lower bounds; Algorithm; Mathematics; Applied mathematics; Machine learning; Mathematical optimization; 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":[0.008302898,0.001345857,0.002772473,0.0008540936,0.001150065,0.002719716,0.003358811,0.002525614,0.003175863],"category_scores_gemma":[0.02582892,0.0007564235,0.001361947,0.001059869,0.001980603,0.004704131,0.003535562,0.003194514,0.001053769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001720531,"about_ca_system_score_gemma":0.001821695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002557153,"about_ca_topic_score_gemma":0.002764326,"domain_scores_codex":[0.9957497,0.001887335,0.0001794605,0.0009341636,0.0009084409,0.0003408971],"domain_scores_gemma":[0.9876673,0.008910266,0.000714001,0.001380948,0.0009522687,0.00037519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004196895,0.0001419466,0.001926865,0.0001760744,0.0001392175,0.00008711754,0.0002449662,0.7560197,0.001881277,0.09748235,0.005942663,0.1355381],"study_design_scores_gemma":[0.00001410742,0.00003211784,0.000097689,0.00001246224,0.000009840642,0.00001762457,0.00001581545,0.9631116,0.0006261052,0.03560898,0.000446447,0.000007134247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04757366,0.0004988295,0.9462913,0.0008447507,0.00007299118,0.0000932807,0.0001204585,0.0004839942,0.004020769],"genre_scores_gemma":[0.7434406,0.0003414426,0.246173,0.0008452059,0.0002675859,0.0003373119,0.0006891117,0.0004672806,0.007438468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008302898,"threshold_uncertainty_score":0.04391044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03040209435461501,"score_gpt":0.1859151147798472,"score_spread":0.1555130204252322,"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."}}