{"id":"W2891786606","doi":"","title":"Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Waterloo; McMaster University","funders":"","keywords":"Upper and lower bounds; Compression (physics); Sample complexity; Mixture model; Matching (statistics); Sample (material); Mathematics; Data compression; Combinatorics; Algorithm; Computer science; Statistics; Artificial intelligence; Physics; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0004603648,0.0001911003,0.0002909377,0.0001754004,0.0007981953,0.0007742079,0.0005561773,0.00009384245,0.000009394435],"category_scores_gemma":[0.0003011581,0.0001557619,0.00007398738,0.0003799855,0.0001488707,0.002426972,0.0001159062,0.0002239206,0.00001190752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003073948,"about_ca_system_score_gemma":0.00007527573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005273401,"about_ca_topic_score_gemma":0.000004343495,"domain_scores_codex":[0.9983081,0.0001039354,0.0006444057,0.000211024,0.0004107606,0.0003218023],"domain_scores_gemma":[0.9982053,0.0002285476,0.0006908387,0.000268676,0.0005172863,0.00008936733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001840437,0.0001714234,0.01118072,0.004758275,0.00008452208,9.996066e-7,0.02650695,0.01548016,0.006468914,0.03365728,0.004841701,0.896665],"study_design_scores_gemma":[0.0003915619,0.0002480127,0.0005877678,0.0001666574,0.000005629261,0.00001468577,0.0001002516,0.9462849,0.001854139,0.000643988,0.04951487,0.0001875153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01553827,0.0001219074,0.982325,0.0002995357,0.0006338041,0.0002929959,0.00002057318,0.0003314833,0.0004364857],"genre_scores_gemma":[0.9357055,0.000001122649,0.06364767,0.0001371689,0.0002901427,0.00003019576,0.00009398648,0.00001068802,0.00008350309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9308048,"threshold_uncertainty_score":0.7465705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0251193021852036,"score_gpt":0.2861917601460713,"score_spread":0.2610724579608677,"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."}}