{"id":"W4315489128","doi":"10.1109/cdc51059.2022.9992906","title":"Bandit learning with regularized second-order mirror descent","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Huawei Technologies","keywords":"Descent (aeronautics); Computer science; Order (exchange); Gradient descent; Artificial intelligence; Mathematical optimization; Applied mathematics; Mathematics; Physics; Artificial neural network","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003880769,0.0004560581,0.0008829482,0.0007835688,0.00153768,0.0007648322,0.001379074,0.0001225285,0.02609162],"category_scores_gemma":[0.001922396,0.0003304316,0.0001691263,0.001550093,0.0003152298,0.000411595,0.000416206,0.001478217,0.0004107008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001779761,"about_ca_system_score_gemma":0.0004195536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003554677,"about_ca_topic_score_gemma":0.000213019,"domain_scores_codex":[0.9908709,0.001092976,0.0009287322,0.001548052,0.004717293,0.0008420459],"domain_scores_gemma":[0.9940822,0.003035589,0.0004447031,0.001097499,0.000854492,0.0004855186],"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":[0.01613026,0.0008671801,0.004272534,0.00001720298,0.0002552529,0.0008739954,0.001442425,0.008155948,0.01824477,0.003288386,0.01306698,0.9333851],"study_design_scores_gemma":[0.04227063,0.007891536,0.02271574,0.0001600026,0.0001161585,0.0004527163,0.01246872,0.3556631,0.001605558,0.05300369,0.5011129,0.00253932],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5412009,0.0006829439,0.44139,0.00467918,0.001928741,0.00259282,0.0003223091,0.0003098477,0.006893168],"genre_scores_gemma":[0.9737908,0.00007528987,0.002176002,0.000942906,0.00007263265,0.000288854,0.00001451478,0.00005305439,0.0225859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9308457,"threshold_uncertainty_score":0.9999148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07159991721118657,"score_gpt":0.3584330874760927,"score_spread":0.2868331702649061,"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."}}