{"id":"W3211530479","doi":"","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multinomial logistic regression; Regret; Outcome (game theory); Computer science; Probabilistic logic; Logistic regression; Algorithm; Click-through rate; Revenue; Combinatorics; Mathematics; Artificial intelligence; Machine learning; Discrete mathematics; Mathematical economics; Information retrieval; Economics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001025593,0.0002301756,0.0003732739,0.0003413953,0.0004402034,0.0001516565,0.0009329796,0.0001701667,0.0006494885],"category_scores_gemma":[0.004550162,0.0001999459,0.0002741844,0.001601151,0.0002727943,0.0004126797,0.0002812897,0.0002519038,0.0003687571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001961877,"about_ca_system_score_gemma":0.0004018956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001916877,"about_ca_topic_score_gemma":0.00005531097,"domain_scores_codex":[0.9971042,0.0002857075,0.0003492305,0.001219909,0.0004683846,0.0005725966],"domain_scores_gemma":[0.9944307,0.002997242,0.0002106832,0.0009612998,0.001103512,0.0002966102],"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":[0.001835997,0.0010175,0.01399672,0.00007279404,0.000138137,0.005123082,0.0002382264,0.8525462,0.002896316,0.01050859,0.02002507,0.09160135],"study_design_scores_gemma":[0.003622112,0.0001676784,0.002555351,0.00003819688,0.00003273367,0.0000108528,0.0004699567,0.9341701,0.007987352,0.03140034,0.01913549,0.0004098052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06136786,0.00007053458,0.9365673,0.000237731,0.0006153921,0.0003330774,0.0001026782,0.00008697029,0.0006184407],"genre_scores_gemma":[0.9791237,0.00001824534,0.007169648,0.00010711,0.000207775,0.000002650037,0.00003740812,0.0000238811,0.01330959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9293976,"threshold_uncertainty_score":0.8153557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4419464955917354,"score_gpt":0.360482215254491,"score_spread":0.08146428033724445,"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."}}