{"id":"W2150394007","doi":"","title":"From PAC-Bayes Bounds to KL Regularization","year":2009,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Coordinate descent; Regularization (linguistics); Mathematics; Boosting (machine learning); Upper and lower bounds; Convex function; Algorithm; Proximal gradient methods for learning; Bayes' theorem; Regular polygon; Elastic net regularization; Mathematical optimization; Applied mathematics; Kullback–Leibler divergence; Computer science; Convex optimization; Artificial intelligence; Regression; Convex combination; Statistics; Bayesian probability; Mathematical analysis","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":[0.006563681,0.002052724,0.001800296,0.001231915,0.000863083,0.003549679,0.002321857,0.002192781,0.005862392],"category_scores_gemma":[0.03285972,0.0009877068,0.0009593806,0.001342683,0.003084677,0.005445697,0.003039035,0.005713287,0.002177077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002819974,"about_ca_system_score_gemma":0.002226556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00235345,"about_ca_topic_score_gemma":0.00249501,"domain_scores_codex":[0.9948384,0.002179488,0.0001814779,0.000647746,0.001823978,0.000328853],"domain_scores_gemma":[0.9889182,0.007299952,0.0006785753,0.001200909,0.001646305,0.0002559665],"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":[0.0001052862,0.00008275906,0.0005921226,0.0002170157,0.0000647389,0.0001117969,0.000151442,0.4584001,0.001463513,0.4422358,0.01119221,0.08538318],"study_design_scores_gemma":[0.000009878911,0.00002044513,0.00009229667,0.00003811983,0.000009440738,0.00004303601,0.000009273902,0.8173837,0.0008502533,0.1791852,0.002345156,0.00001324126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00189681,0.0006431086,0.9919431,0.0005241516,0.0000638109,0.00002113068,0.00004193115,0.0002904955,0.004575389],"genre_scores_gemma":[0.3385999,0.002430468,0.6379496,0.002124436,0.0007852017,0.000677712,0.0005303917,0.0015225,0.01537983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006563681,"threshold_uncertainty_score":0.03471249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00881585654239763,"score_gpt":0.2416711849258008,"score_spread":0.2328553283834032,"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."}}