{"id":"W2963375484","doi":"","title":"PAC-Bayes bounds for stable algorithms with instance-dependent priors","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Defence Science and Technology Group; DeepMind; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Simons Institute for the Theory of Computing, University of California Berkeley; Office of Defense Programs; Multidisciplinary University Research Initiative; Engineering and Physical Sciences Research Council; Defence Science and Technology Laboratory; U.S. Department of Defense; Alberta Innovates; Alberta Machine Intelligence Institute","keywords":"Prior probability; Bayes' theorem; Stability (learning theory); Algorithm; Mathematics; Gaussian; Artificial intelligence; Computer science; Upper and lower bounds; Naive Bayes classifier; Classifier (UML); Pattern recognition (psychology); Bayesian probability; Support vector machine; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00326434,0.0002304195,0.0002310052,0.0001328042,0.000753207,0.0006526837,0.001435083,0.00008337612,0.00005103001],"category_scores_gemma":[0.0004415054,0.000201884,0.00008196535,0.0005681333,0.0002439074,0.0004517023,0.0003648538,0.0002311108,0.00004318298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007209655,"about_ca_system_score_gemma":0.0002260612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005122137,"about_ca_topic_score_gemma":0.000969787,"domain_scores_codex":[0.9970021,0.001083736,0.0002974195,0.0006907906,0.0004470739,0.0004788762],"domain_scores_gemma":[0.9957624,0.0006604655,0.000248952,0.001504221,0.001641185,0.0001827681],"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":[0.00003947925,0.0007234829,0.003722389,0.00008969082,0.0001150711,0.000009757964,0.01941405,0.00007498939,0.001823977,0.3803768,0.002542228,0.5910681],"study_design_scores_gemma":[0.003432744,0.00002290386,0.004712541,0.001028579,0.00004664085,0.00007509338,0.0003933867,0.5762724,0.1203551,0.01023447,0.2820868,0.001339312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01840845,0.0001944899,0.9529787,0.005961781,0.0002155725,0.000312402,0.00001416075,0.0003945551,0.02151985],"genre_scores_gemma":[0.4646721,0.00004432287,0.5178433,0.0001909446,0.0000690054,0.00006792325,0.00003430345,0.00003456854,0.0170435],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5897288,"threshold_uncertainty_score":0.8232589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00848001380485293,"score_gpt":0.2249546404959976,"score_spread":0.2164746266911447,"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."}}