{"id":"W2964072175","doi":"10.14288/1.0044651","title":"Online learning under delayed feedback","year":2015,"lang":"en","type":"article","venue":"Open Collections","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Online learning; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Multimedia","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":[0.002851072,0.001095385,0.001439335,0.0004804369,0.0004936462,0.001549078,0.001369619,0.001666501,0.001952905],"category_scores_gemma":[0.01728046,0.0004428048,0.0004736886,0.0006349812,0.001550764,0.002487736,0.001438605,0.002047843,0.0003438327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001904469,"about_ca_system_score_gemma":0.00136327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001635288,"about_ca_topic_score_gemma":0.00104948,"domain_scores_codex":[0.9983501,0.0006396045,0.00007026507,0.0003667228,0.000313738,0.0002595758],"domain_scores_gemma":[0.9896495,0.008020634,0.0008192835,0.000595984,0.000604357,0.0003101197],"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":[0.0003484336,0.00007997084,0.0005944065,0.0002208837,0.00005694367,0.00009542183,0.00006039538,0.8727888,0.001398167,0.09774462,0.001691498,0.0249204],"study_design_scores_gemma":[0.00004051899,0.0000666117,0.00008984261,0.00001826674,0.00001395136,0.00002357293,0.000007385056,0.9454207,0.0006466676,0.05318409,0.0004812438,0.000007095653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05209151,0.001592718,0.9404638,0.0009728308,0.0001509231,0.00005948878,0.0001464279,0.0003915255,0.004130785],"genre_scores_gemma":[0.9507481,0.0009133728,0.04358191,0.0002771584,0.0001834405,0.0001508169,0.00009779445,0.0000655221,0.003981859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002851072,"threshold_uncertainty_score":0.01507807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2615616721285479,"score_gpt":0.4801871304299516,"score_spread":0.2186254583014037,"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."}}