{"id":"W2160262323","doi":"10.48550/arxiv.1306.0686","title":"Online Learning under Delayed Feedback","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Online learning; Computer science; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Multimedia; World Wide Web","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":[0.002581404,0.001013841,0.001310593,0.0004577789,0.0004877316,0.001521799,0.001279406,0.001603612,0.001858766],"category_scores_gemma":[0.01641861,0.0004202592,0.0004481882,0.0006123792,0.001488942,0.002427549,0.001407038,0.002005178,0.0003275278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001891523,"about_ca_system_score_gemma":0.00128136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001509497,"about_ca_topic_score_gemma":0.0009661043,"domain_scores_codex":[0.9984258,0.0006215355,0.00006581825,0.0003635857,0.0002918004,0.0002314234],"domain_scores_gemma":[0.9907715,0.007105915,0.0007309522,0.0006002922,0.0005193117,0.0002720038],"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":[0.0003835937,0.00008576029,0.0007067217,0.0002199799,0.00005962134,0.00009111931,0.00006499452,0.844573,0.001607165,0.1227994,0.001860821,0.0275479],"study_design_scores_gemma":[0.00003927886,0.00006162743,0.00009318207,0.00001693696,0.00001299455,0.0000222432,0.000007441031,0.9322973,0.0007163723,0.06623557,0.0004903438,0.000006727676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05890769,0.001452055,0.9333338,0.001122851,0.0001488134,0.00005846771,0.0001546861,0.0003982905,0.004423437],"genre_scores_gemma":[0.9511653,0.0008245999,0.04341134,0.0002771195,0.0001760072,0.0001382328,0.00009999602,0.00006424671,0.003843241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002581404,"threshold_uncertainty_score":0.01372403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2569419831242067,"score_gpt":0.3170267194651759,"score_spread":0.06008473634096922,"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."}}