{"id":"W4380136285","doi":"10.48550/arxiv.2306.04923","title":"Unconstrained Online Learning with Unbounded Losses","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regret; Lipschitz continuity; Bounded function; Saddle point; Mathematics; Leverage (statistics); Domain (mathematical analysis); Combinatorics; Upper and lower bounds; Matching (statistics); Saddle; Mathematical optimization; Discrete mathematics; Computer science; Pure mathematics; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00304008,0.001283565,0.00142004,0.0005707975,0.0007008591,0.001797536,0.002125848,0.001818877,0.004245212],"category_scores_gemma":[0.01461892,0.0006723349,0.0007804961,0.0009936923,0.001775023,0.00367479,0.00277582,0.003839446,0.001350707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001432316,"about_ca_system_score_gemma":0.001485171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001385279,"about_ca_topic_score_gemma":0.001278275,"domain_scores_codex":[0.9980604,0.0008516723,0.00008522292,0.000451528,0.0003827855,0.0001683858],"domain_scores_gemma":[0.9933491,0.00504791,0.0003154181,0.0007721925,0.0003053605,0.0002098636],"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":[0.0002277637,0.0001682143,0.0005614988,0.0001899183,0.00005095772,0.0001283906,0.00007889875,0.7340587,0.001192612,0.1893921,0.007193617,0.0667574],"study_design_scores_gemma":[0.00001605367,0.00001790022,0.00005286597,0.00001218224,0.000003358198,0.0000170598,0.000005155874,0.937034,0.0004198853,0.06149328,0.0009237755,0.000004616778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01016743,0.0003607263,0.9829016,0.000718632,0.00006350356,0.00005141826,0.00009605373,0.0004542078,0.005186449],"genre_scores_gemma":[0.5602412,0.000719822,0.4228363,0.0007719138,0.0002620433,0.0004676516,0.0006895682,0.0004106588,0.01360084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004245212,"threshold_uncertainty_score":0.01607764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3545191683132599,"score_gpt":0.3271747835432784,"score_spread":0.02734438476998141,"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."}}