{"id":"W4396780329","doi":"10.1016/j.jfranklin.2024.106884","title":"Online composite optimization with time-varying regularizers","year":2024,"lang":"en","type":"article","venue":"Journal of the Franklin Institute","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Regret; Metric (unit); Path (computing); Convex optimization; Upper and lower bounds; Function (biology); Regular polygon; Variation (astronomy); Convex function; Mathematical optimization; Mathematics; Computer science; Optimization problem; Online algorithm; Combinatorics; Statistics; Mathematical analysis; Physics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001814145,0.0001339608,0.0002858403,0.0004076995,0.0002413304,0.0004482064,0.00118286,0.00006452457,0.0001832221],"category_scores_gemma":[0.0008571236,0.00006417077,0.0001944323,0.001487118,0.0002907212,0.001271787,0.000165832,0.0006072185,0.00007768952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001133678,"about_ca_system_score_gemma":0.0003351861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004380215,"about_ca_topic_score_gemma":0.000004372917,"domain_scores_codex":[0.9965693,0.0001554586,0.0006918674,0.0002206278,0.002153078,0.0002096578],"domain_scores_gemma":[0.9980612,0.0004501356,0.0003230438,0.0004216286,0.0006312439,0.0001127798],"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":[0.0001373829,0.00005139953,0.00008249367,0.000007080183,0.00007704291,0.0001603724,0.0001335117,0.9824434,0.0007912162,0.00005748087,0.002338749,0.0137199],"study_design_scores_gemma":[0.00108664,0.0002227297,0.0007557162,0.0006638253,0.00008442142,0.001171534,0.0000767114,0.8945853,0.001921326,0.004814741,0.09439013,0.000226993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02653936,0.001281487,0.9625371,0.005812707,0.002810673,0.0002696004,0.00002371343,0.00003606966,0.0006893072],"genre_scores_gemma":[0.4941504,0.0003797052,0.4779792,0.0009102445,0.003462861,0.00000994545,0.0000153817,0.0001154918,0.02297683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4845579,"threshold_uncertainty_score":0.4322065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0543017719601523,"score_gpt":0.3727089263373512,"score_spread":0.3184071543771989,"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."}}