{"id":"W3008672633","doi":"10.4171/msl/38","title":"Optimal anytime regret with two experts","year":2023,"lang":"en","type":"article","venue":"Mathematical Statistics and Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Minimax; Time horizon; Constant (computer programming); Mathematical optimization; Computer science; Horizon; 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":["insufficient_payload"],"category_scores_codex":[0.001883737,0.0001335481,0.0002816176,0.0001657239,0.000355232,0.0003260845,0.0002267239,0.00003628831,0.001185501],"category_scores_gemma":[0.006583154,0.00008253749,0.00002131778,0.0006355649,0.0002300216,0.00008428015,0.0001868737,0.0003043191,0.0008940107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001633088,"about_ca_system_score_gemma":0.00002942725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004506176,"about_ca_topic_score_gemma":0.000002176424,"domain_scores_codex":[0.9973917,0.0001767225,0.0003347673,0.0003809112,0.001312822,0.0004030943],"domain_scores_gemma":[0.9946053,0.0046907,0.00008998544,0.0002321419,0.000180214,0.0002016293],"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":[0.0002773062,0.0002210483,0.003553493,0.0001577559,0.0001217139,0.001945654,0.01368936,0.1174604,0.0003894237,0.1261144,0.03354051,0.702529],"study_design_scores_gemma":[0.0005794237,0.0002846917,0.00112684,0.00004126255,0.000007493186,0.00005544981,0.00266978,0.8703772,0.00003934944,0.1123375,0.01225708,0.0002239238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07777894,0.00002750017,0.9198385,0.0002788625,0.000025544,0.0001347164,0.0000206961,0.0001019466,0.001793223],"genre_scores_gemma":[0.4784819,0.00002409277,0.4882969,0.00006205225,0.0001350292,0.00004490003,0.00002256206,0.00006290474,0.03286966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7529168,"threshold_uncertainty_score":0.9998839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09688300321347229,"score_gpt":0.437329077888751,"score_spread":0.3404460746752787,"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."}}