{"id":"W2963750948","doi":"","title":"Differentially Private Contextual Linear Bandits","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Differential privacy; Thompson sampling; Context (archaeology); Computer science; Mathematical optimization; Noise (video); Tree (set theory); Mathematics; Theoretical computer science; Artificial intelligence; Algorithm; Machine learning; Combinatorics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003775607,0.001061395,0.002035084,0.0004640626,0.0008442416,0.002237628,0.002300804,0.002451705,0.002315479],"category_scores_gemma":[0.01740778,0.0006170945,0.000897755,0.001138682,0.002374559,0.00380311,0.00329646,0.00307108,0.0007485072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001777222,"about_ca_system_score_gemma":0.00143011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001234066,"about_ca_topic_score_gemma":0.001201718,"domain_scores_codex":[0.9957826,0.001973855,0.0001662721,0.0008357183,0.0006972693,0.00054426],"domain_scores_gemma":[0.9918144,0.005374057,0.0006364507,0.001492168,0.000427663,0.0002552049],"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":[0.0007739348,0.0001724681,0.001532221,0.0001932606,0.00009212593,0.0001435493,0.0002516154,0.6523973,0.003567733,0.2806709,0.003363708,0.05684128],"study_design_scores_gemma":[0.00004044394,0.00004704164,0.0001191561,0.00001595345,0.00001349758,0.00003659095,0.00001885076,0.9049366,0.001382163,0.09248,0.0008976245,0.00001213474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03851521,0.0005555167,0.9556997,0.001053588,0.00006688453,0.0000739985,0.0002147113,0.000542877,0.003277557],"genre_scores_gemma":[0.8655237,0.0004847774,0.1285816,0.0005643513,0.0001531884,0.000237221,0.0003324967,0.0001113169,0.004011225],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003775607,"threshold_uncertainty_score":0.01996756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07113055450997233,"score_gpt":0.2052884025406932,"score_spread":0.1341578480307208,"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."}}