{"id":"W4392270931","doi":"10.48550/arxiv.2402.17235","title":"Stochastic Gradient Succeeds for Bandits","year":2024,"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; Canadian Institute for Advanced Research","keywords":"Mathematical economics; Computer science; Economics; Econometrics; Mathematics","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":[0.002769903,0.001246291,0.001371899,0.0007795065,0.0008810641,0.001698887,0.0009449414,0.001427724,0.0039115],"category_scores_gemma":[0.01992323,0.0004674334,0.0006829069,0.0007421343,0.002164174,0.002158225,0.001837485,0.002464056,0.001126239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294277,"about_ca_system_score_gemma":0.00172278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002785512,"about_ca_topic_score_gemma":0.002471162,"domain_scores_codex":[0.99837,0.0006370917,0.00008133884,0.0002767012,0.0004146339,0.000220267],"domain_scores_gemma":[0.9928871,0.005245721,0.000566986,0.0005984021,0.0004838504,0.0002179329],"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":[0.0002958668,0.0001124666,0.001059228,0.0001878701,0.00007212869,0.0001326254,0.0001542942,0.5915805,0.003222218,0.3338252,0.003512797,0.06584489],"study_design_scores_gemma":[0.00001672845,0.00003905236,0.00008649885,0.00002046585,0.000009034274,0.00002474616,0.000009116112,0.925966,0.0008390531,0.07203738,0.0009442,0.000007722281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03033372,0.000489118,0.9580398,0.000859183,0.0001008797,0.00007122052,0.00005544676,0.0004852014,0.009565424],"genre_scores_gemma":[0.781611,0.0008128796,0.2044927,0.0006967697,0.0002103283,0.0003415939,0.0001579563,0.0003727929,0.01130405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0039115,"threshold_uncertainty_score":0.0146488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2906479033614339,"score_gpt":0.3273040213724201,"score_spread":0.03665611801098623,"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."}}