{"id":"W2972039342","doi":"10.1109/ita50056.2020.9244945","title":"Differentially Private Algorithms for Learning Mixtures of Separated Gaussians","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Simons Institute for the Theory of Computing, University of California Berkeley; Microsoft Research; University of Alberta; National Science Foundation","keywords":"Differential privacy; Mixture model; Sample complexity; Constraint (computer-aided design); A priori and a posteriori; Algorithm; Gaussian; Range (aeronautics); Computer science; Sample (material); Artificial intelligence; Mathematics; Physics; Engineering","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":[0.006087866,0.00122161,0.001769844,0.001354779,0.001371566,0.00295085,0.003325028,0.002801789,0.00192672],"category_scores_gemma":[0.0292216,0.0008583614,0.001358353,0.001995391,0.003488677,0.007636221,0.006738984,0.005349428,0.0008780563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002780981,"about_ca_system_score_gemma":0.001884646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005801262,"about_ca_topic_score_gemma":0.0005799963,"domain_scores_codex":[0.9932716,0.002572387,0.0003589642,0.001195336,0.00211118,0.0004904331],"domain_scores_gemma":[0.9814011,0.01173973,0.0009853703,0.004705891,0.0008194607,0.000348522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006444428,0.0001697574,0.001143374,0.0001893277,0.0001275533,0.0001386323,0.0003624573,0.25531,0.006505033,0.6070479,0.00351302,0.1248486],"study_design_scores_gemma":[0.00006280595,0.00004417375,0.0001047441,0.00001570387,0.00001693459,0.0000904957,0.00001974393,0.626827,0.003369278,0.3679221,0.001504114,0.0000228927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005071631,0.000188823,0.9934783,0.000326252,0.0000236681,0.0000319825,0.0000619667,0.000218755,0.0005986656],"genre_scores_gemma":[0.4564011,0.0008868758,0.5361546,0.0006147895,0.0003270985,0.0004366217,0.0006085488,0.0002237516,0.004346633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006087866,"threshold_uncertainty_score":0.0321961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05572315081656393,"score_gpt":0.3125892285517211,"score_spread":0.2568660777351571,"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."}}