{"id":"W4414165913","doi":"10.1109/tcns.2025.3608004","title":"One-Point Sampling for Distributed Bandit Convex Optimization With Time-Varying Constraints","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Regret; Sublinear function; Upper and lower bounds; Convex function; Constraint (computer-aided design); Convex optimization; Benchmark (surveying); Projection (relational algebra)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003699805,0.00159951,0.002063759,0.0004371156,0.0006860397,0.001402302,0.001876752,0.001562526,0.002885155],"category_scores_gemma":[0.01224195,0.0008409711,0.0008958093,0.0008217569,0.001728495,0.002187904,0.001856203,0.00298277,0.000575732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710754,"about_ca_system_score_gemma":0.001509105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004856524,"about_ca_topic_score_gemma":0.00405167,"domain_scores_codex":[0.9979895,0.001024782,0.00006801783,0.0003659287,0.000356661,0.000194994],"domain_scores_gemma":[0.9934278,0.004985705,0.0004597152,0.0004309138,0.0004582165,0.0002376205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001996652,0.00008166938,0.0004886956,0.00008259859,0.0000455754,0.00008556528,0.00004623818,0.9523149,0.0005176391,0.02769731,0.001121334,0.01731896],"study_design_scores_gemma":[0.00001003467,0.00001652186,0.00002814077,0.000003504291,0.000002923668,0.000006272153,0.000004031534,0.9937913,0.0001370739,0.005875973,0.0001219187,0.000002321248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01160843,0.0003390264,0.9858942,0.0002746564,0.00004085737,0.00006434366,0.00004534989,0.0002255989,0.001507509],"genre_scores_gemma":[0.7335366,0.0006816909,0.258462,0.0004518745,0.0001593619,0.0005533492,0.0003862591,0.0002475834,0.005521308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004856524,"threshold_uncertainty_score":0.01956671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05865261333941649,"score_gpt":0.3494235832352155,"score_spread":0.290770969895799,"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."}}