{"id":"W4214636767","doi":"10.1109/lcsys.2022.3155067","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","year":2022,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Convexity; Smoothness; Mathematical optimization; Lipschitz continuity; Convex optimization; Convex function; Regularization (linguistics); Upper and lower bounds; Mathematics; Function (biology); Bounded function; Computer science; Regular polygon; Artificial intelligence; Economics; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0030152,0.0002345897,0.0007468408,0.0005407861,0.0005147327,0.00009690609,0.0009584019,0.00006460757,0.0001304423],"category_scores_gemma":[0.001262786,0.0001960549,0.0002942723,0.0008464386,0.0002502029,0.0002550109,0.00009148216,0.0004263747,0.00005173195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005517673,"about_ca_system_score_gemma":0.000174246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001599671,"about_ca_topic_score_gemma":0.00007774853,"domain_scores_codex":[0.9945417,0.0008320137,0.001179254,0.000702013,0.002174294,0.0005707096],"domain_scores_gemma":[0.9943352,0.003397332,0.0007450436,0.0007732573,0.00058257,0.0001665453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003453345,0.0009889097,0.006087966,0.0001817422,0.0007595988,0.0001476699,0.001428908,0.5183588,0.3016806,0.0003631278,0.1511699,0.01537939],"study_design_scores_gemma":[0.01057525,0.0007841444,0.009998361,0.00007287296,0.00008824385,0.00006032235,0.004040323,0.7266194,0.0001363066,0.0003317818,0.2466803,0.0006126419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1101732,0.0004884228,0.8683746,0.008859554,0.004005211,0.0038051,0.00417706,0.00007734875,0.00003952696],"genre_scores_gemma":[0.994419,0.000002843549,0.0006347794,0.0007015659,0.00009398016,0.0009382239,0.0000525451,0.00004175112,0.003115336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8842458,"threshold_uncertainty_score":0.7994885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09309093525136584,"score_gpt":0.3857145837651675,"score_spread":0.2926236485138016,"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."}}