{"id":"W2552858844","doi":"10.48550/arxiv.1702.03040","title":"Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta","keywords":"Sublinear function; Regret; Bounded function; Logarithm; Boundary (topology); Domain (mathematical analysis); Constraint (computer-aided design); Regular polygon; Curvature; Computer science; Algorithm; Mathematical optimization; Mathematics; Upper and lower bounds; Discrete mathematics; Geometry; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005710018,0.001203355,0.001984312,0.0006602696,0.001116864,0.002282594,0.00238143,0.002466483,0.003212008],"category_scores_gemma":[0.03073392,0.0008021898,0.001022173,0.001347606,0.003389236,0.005898815,0.003069181,0.004913235,0.0009112218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001644118,"about_ca_system_score_gemma":0.001548042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001822469,"about_ca_topic_score_gemma":0.001497515,"domain_scores_codex":[0.9977484,0.001173604,0.00006661913,0.0004083919,0.0003421353,0.0002607817],"domain_scores_gemma":[0.9822869,0.01330194,0.001270101,0.001718455,0.0006666936,0.0007559182],"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":[0.0006235631,0.0002094299,0.001881735,0.0001514176,0.00007603076,0.0002170133,0.000302186,0.7600062,0.001430617,0.1829424,0.006070379,0.04608887],"study_design_scores_gemma":[0.00003900149,0.00007790303,0.0001259734,0.0000202404,0.000007987172,0.00003787208,0.00002660688,0.9163042,0.0007363717,0.0821323,0.0004760682,0.00001551656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07460631,0.0007482905,0.9170125,0.001967039,0.00007247616,0.00009170192,0.0001927909,0.000739773,0.004569196],"genre_scores_gemma":[0.7858341,0.0005887485,0.2058978,0.0007721883,0.000171509,0.0002892443,0.0004065739,0.0004276221,0.005612221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005710018,"threshold_uncertainty_score":0.03019786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2529146763771616,"score_gpt":0.3257650853383418,"score_spread":0.07285040896118011,"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."}}