{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003081496,0.0004374144,0.0006997623,0.0002152698,0.0001022299,0.0002760338,0.04398765,0.0005660602,0.0000262703],"category_scores_gemma":[0.01055499,0.0003889592,0.0002445404,0.0003706601,0.0001264992,0.0002077856,0.2231011,0.001101016,0.00001364921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005845696,"about_ca_system_score_gemma":0.0001845864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005538424,"about_ca_topic_score_gemma":0.000004163041,"domain_scores_codex":[0.9970648,0.0001139721,0.0006311107,0.001277532,0.0004320873,0.0004805508],"domain_scores_gemma":[0.9911063,0.0002552569,0.0005505903,0.007822788,0.0001678791,0.00009713147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001572303,0.0005704987,0.00116461,0.003793778,0.00191158,0.0001035247,0.0009204135,0.004679668,0.05076351,0.07690568,0.6697903,0.1892392],"study_design_scores_gemma":[0.0002765883,0.0001223382,0.0002330155,0.000122567,0.00002697344,0.000002575336,0.000004395705,0.6197691,0.04194362,0.3345019,0.002609597,0.0003873703],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002611859,0.0001637312,0.973913,0.01859875,0.0007612989,0.0007755837,0.0001023003,0.002292757,0.0007807146],"genre_scores_gemma":[0.1181505,0.0001161964,0.8809456,0.0001199238,0.00008607793,0.0001198691,0.0002236541,0.00004148306,0.0001967521],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6671807,"threshold_uncertainty_score":0.9998562,"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."}}