{"id":"W2110582581","doi":"10.48550/arxiv.1206.6457","title":"Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Exponential function; Mathematical economics; Applied mathematics; Mathematics; Gaussian; Process (computing); Gaussian process; Econometrics; Mathematical optimization; Statistical physics; Economics; Computer science; Statistics; Physics; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001154892,0.0004544576,0.0006214497,0.000614698,0.0006109455,0.000410073,0.00227595,0.0003814909,0.0002483099],"category_scores_gemma":[0.001119863,0.0003861517,0.0002598037,0.001271235,0.0004985525,0.0008941838,0.0007865838,0.0006844122,0.0001284462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000262731,"about_ca_system_score_gemma":0.0007392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002880701,"about_ca_topic_score_gemma":0.0001668109,"domain_scores_codex":[0.9961184,0.000197749,0.0004982642,0.001624611,0.0007295111,0.0008314147],"domain_scores_gemma":[0.9949721,0.001137442,0.0006281201,0.001602561,0.001218006,0.0004417956],"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":[0.005265761,0.001829164,0.08460134,0.001091339,0.00109931,0.001494933,0.004952717,0.8265898,0.0001760463,0.05210849,0.008619096,0.01217204],"study_design_scores_gemma":[0.004878093,0.0006984707,0.03182301,0.0004491738,0.0006069489,0.0000529332,0.002587059,0.5084091,0.0005371974,0.4323353,0.0149858,0.002636936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2540251,0.00004959971,0.7424408,0.0001427039,0.0007253479,0.001198065,0.0003297789,0.0001179719,0.0009705576],"genre_scores_gemma":[0.9874266,0.00002142161,0.00209412,0.00003233045,0.0003948862,0.00002594721,0.0001252373,0.00005479125,0.009824689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7403467,"threshold_uncertainty_score":0.999859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4019517217496925,"score_gpt":0.3403438641409024,"score_spread":0.06160785760879012,"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."}}