{"id":"W4294691466","doi":"10.23919/acc53348.2022.9867309","title":"Dynamic Regret Bounds without Lipschitz Continuity: Online Convex Optimization with Multiple Mirror Descent Steps","year":2022,"lang":"en","type":"article","venue":"2022 American Control Conference (ACC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Lipschitz continuity; Path (computing); Mathematical optimization; Convex optimization; Upper and lower bounds; Gradient descent; Mathematics; Path length; Sequence (biology); Regular polygon; Computer science; Artificial intelligence; Statistics; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002299363,0.000579975,0.001412831,0.0007238416,0.001025519,0.0006654811,0.002279159,0.00007256603,0.003801754],"category_scores_gemma":[0.002606535,0.0004716684,0.0002207116,0.002681609,0.001348816,0.0006514722,0.0007234126,0.001259731,0.00008075182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006065309,"about_ca_system_score_gemma":0.001276575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008757462,"about_ca_topic_score_gemma":0.003058136,"domain_scores_codex":[0.9901565,0.001499557,0.001176226,0.001676557,0.004314193,0.001176944],"domain_scores_gemma":[0.9932284,0.001859987,0.001263852,0.001605082,0.001536062,0.0005066681],"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":[0.01270785,0.002683025,0.2217558,0.00004009984,0.0008890731,0.0006566171,0.003581388,0.2612971,0.005180717,0.0007261221,0.002718933,0.4877633],"study_design_scores_gemma":[0.006247683,0.001772364,0.01784286,0.00002309022,0.00006715408,0.0000739924,0.01092247,0.9400046,0.00003669673,0.0002855326,0.02195865,0.0007649071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2308926,0.0002949944,0.7579706,0.00460131,0.0006419172,0.002594169,0.002009432,0.0003547612,0.0006402944],"genre_scores_gemma":[0.9761837,0.00005744219,0.0177002,0.001003382,0.00005418911,0.0004702194,0.0002278193,0.00008837804,0.004214728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7452911,"threshold_uncertainty_score":0.9997735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0478450906761866,"score_gpt":0.3652658143209036,"score_spread":0.317420723644717,"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."}}