{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002236581,0.0001569924,0.0001933354,0.000079909,0.0002506106,0.00004617226,0.01310735,0.00008298243,0.00009472141],"category_scores_gemma":[0.006611752,0.0001341196,0.00007373886,0.001029595,0.0004444389,0.0003414456,0.02249192,0.0004202994,0.00007775819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006459028,"about_ca_system_score_gemma":0.00006276438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001389717,"about_ca_topic_score_gemma":0.000007880371,"domain_scores_codex":[0.9986735,0.0001608331,0.0001530023,0.0005892187,0.0001501197,0.0002733433],"domain_scores_gemma":[0.9961348,0.0006420973,0.0001692969,0.002895467,0.00007082409,0.00008750433],"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":[0.00003968658,0.00004705351,0.001151071,0.000010823,0.00003532585,0.00004276275,0.00005179518,0.006841355,0.0004489539,0.9828176,0.008260651,0.0002529283],"study_design_scores_gemma":[0.0002770186,0.0001363657,0.001708727,0.00001654033,0.00000739531,0.000001190099,0.0000280309,0.4330383,0.002449665,0.5618024,0.000394859,0.0001395708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5113287,0.000007184549,0.4665995,0.02078683,0.00008895038,0.0001401799,0.00002102645,0.0004842531,0.0005433545],"genre_scores_gemma":[0.9782779,0.000008347645,0.02114809,0.000510005,0.00001274282,2.694481e-7,0.000008994044,0.000008262161,0.00002536296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4669492,"threshold_uncertainty_score":0.9922322,"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."}}