{"id":"W3149949875","doi":"","title":"On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians.","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McMaster University","funders":"","keywords":"Cover (algebra); Constraint (computer-aided design); Sample complexity; Multivariate normal distribution; Distribution (mathematics); Sample (material); Covariance; Sample space; Computer science; Differential privacy; Mixture model; Upper and lower bounds; Space (punctuation); Mathematics; Identity (music); Multivariate statistics; Mathematical optimization; Artificial intelligence; Theoretical computer science; Algorithm; Machine learning; Statistics","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":[0.01386363,0.002113044,0.003108875,0.002079198,0.001859541,0.005742668,0.004511549,0.003341111,0.004832984],"category_scores_gemma":[0.1224955,0.001178895,0.002192887,0.002606926,0.006493839,0.01346639,0.007923456,0.009526966,0.0008559088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006644536,"about_ca_system_score_gemma":0.003843504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001791354,"about_ca_topic_score_gemma":0.002068937,"domain_scores_codex":[0.9905052,0.003650303,0.0004117733,0.001388328,0.002922379,0.001122102],"domain_scores_gemma":[0.8038981,0.177102,0.004549918,0.00980775,0.00252312,0.002119077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001306478,0.0004394714,0.006357081,0.0007854634,0.0003911799,0.0003639284,0.000711246,0.407838,0.005808925,0.508558,0.007730648,0.05970957],"study_design_scores_gemma":[0.00006019529,0.0001373469,0.0009189065,0.0000875929,0.00005279902,0.0001772667,0.00007851133,0.6043938,0.001836691,0.3908162,0.001401575,0.00003914092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06763981,0.0036156,0.9064056,0.006818263,0.0002061556,0.0003017913,0.001215337,0.0005989671,0.01319843],"genre_scores_gemma":[0.8411922,0.003638829,0.1438057,0.001809197,0.0009298165,0.001173905,0.001783643,0.0003432674,0.005323378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01386363,"threshold_uncertainty_score":0.07331872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1519281379634141,"score_gpt":0.2036543756345726,"score_spread":0.05172623767115853,"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."}}