{"id":"W3091802565","doi":"10.1145/3417994","title":"Near-optimal Sample Complexity Bounds for Robust Learning of Gaussian Mixtures via Compression Schemes","year":2020,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of British Columbia; University of Waterloo; McMaster University; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Upper and lower bounds; Compression (physics); Gaussian; Sample complexity; Matching (statistics); Mathematics; Scheme (mathematics); Data compression; Algorithm; Class (philosophy); Computer science; Distribution (mathematics); Artificial intelligence; Statistics; Mathematical analysis; Physics","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":[0.01047842,0.003214525,0.003248774,0.002781563,0.001214715,0.003760573,0.004301035,0.003439352,0.00525301],"category_scores_gemma":[0.08424353,0.00137759,0.00200798,0.002680292,0.004930072,0.01131969,0.008592726,0.008715078,0.001436618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004284321,"about_ca_system_score_gemma":0.002872596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001568001,"about_ca_topic_score_gemma":0.001637437,"domain_scores_codex":[0.9915192,0.002335581,0.000432923,0.001254246,0.003672842,0.0007851595],"domain_scores_gemma":[0.940284,0.04835927,0.002263736,0.005657926,0.002257438,0.001177673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000886512,0.0003259648,0.002209328,0.0004727708,0.000172939,0.0002205142,0.0002850481,0.6549283,0.008278436,0.2288228,0.005548103,0.09784938],"study_design_scores_gemma":[0.00003093786,0.00007933752,0.0002356871,0.00004405093,0.0000193389,0.00007928858,0.00001889634,0.9194166,0.002427734,0.07667058,0.0009514858,0.00002610928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01285719,0.001381834,0.9792024,0.001157477,0.00007993784,0.0001442177,0.0001897668,0.0007400642,0.004247062],"genre_scores_gemma":[0.4839809,0.002889719,0.5007073,0.001693138,0.0009300708,0.001262014,0.001441146,0.0009778836,0.006117815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01047842,"threshold_uncertainty_score":0.05541587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04636202812958371,"score_gpt":0.2856437907121075,"score_spread":0.2392817625825238,"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."}}