{"id":"W2206616202","doi":"","title":"Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Lasso (programming language); Online algorithm; Algorithm; Set (abstract data type); Online learning; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001189412,0.0001316047,0.0002064235,0.000406285,0.0001884968,0.0001084004,0.0005194116,0.00005941687,0.0008498661],"category_scores_gemma":[0.002758978,0.0000960667,0.00003312982,0.001013526,0.00009085306,0.0004671031,0.0003694078,0.0001334682,0.005033597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005195905,"about_ca_system_score_gemma":0.00004837747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006163566,"about_ca_topic_score_gemma":0.00007699803,"domain_scores_codex":[0.9974337,0.0000690037,0.0003342888,0.0004667686,0.001207209,0.0004889795],"domain_scores_gemma":[0.9969792,0.001240937,0.00005899273,0.0005793135,0.0003150044,0.0008265782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005803002,0.001428969,0.02195817,0.00002757781,0.00009145971,0.00001813167,0.0156629,0.04713886,0.01385339,0.02232618,0.2756282,0.6012859],"study_design_scores_gemma":[0.003277651,0.001074057,0.3069449,0.00009684642,0.0000620678,0.0001449549,0.02334376,0.165134,0.007764854,0.04312858,0.44664,0.002388301],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08970872,0.00004695997,0.9067177,0.002082905,0.0002126839,0.0006194789,0.00006161517,0.00004592636,0.0005039787],"genre_scores_gemma":[0.9849985,0.000003962524,0.009343336,0.0007402891,0.0002190811,0.00005449564,0.000008993724,0.00001163044,0.004619703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8973744,"threshold_uncertainty_score":0.9957411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1421157769493659,"score_gpt":0.4560052028147418,"score_spread":0.3138894258653759,"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."}}