{"id":"W2963714521","doi":"10.1109/tpami.2018.2885760","title":"Flexible High-Dimensional Unsupervised Learning with Missing Data","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; Texas Commission on Environmental Quality; U.S. Environmental Protection Agency","keywords":"Missing data; Imputation (statistics); Computer science; Expectation–maximization algorithm; Mixture model; Curse of dimensionality; Unsupervised learning; Artificial intelligence; Generalization; Data modeling; Gaussian; Pattern recognition (psychology); Data mining; Algorithm; Machine learning; Mathematics; Statistics; Maximum likelihood","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":[],"consensus_categories":[],"category_scores_codex":[0.0004588201,0.0002281577,0.0003112382,0.0003703485,0.0004349794,0.0002040137,0.0007339102,0.00006138642,0.0001853741],"category_scores_gemma":[0.000004610062,0.0001713656,0.0000845628,0.001091551,0.0001270189,0.0004040783,0.00001997601,0.0003205014,0.0000247776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001596742,"about_ca_system_score_gemma":0.0000382318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00104541,"about_ca_topic_score_gemma":0.0005928024,"domain_scores_codex":[0.9981678,0.0001657199,0.0002774864,0.0008088606,0.0003106433,0.0002694585],"domain_scores_gemma":[0.9985359,0.0001271203,0.00008613703,0.0009790866,0.0001098992,0.0001618147],"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":[0.00001930506,0.00007933617,0.0001644002,0.000007249474,0.0003244621,0.000009611147,0.0001900604,0.004345108,0.0004568181,0.0001867204,0.000009843084,0.9942071],"study_design_scores_gemma":[0.0001451595,0.0003075571,0.0004438561,0.0000435926,0.0004188937,0.00002852873,0.00001046369,0.8893094,0.1078807,0.0009354919,0.0001452664,0.0003310837],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00162806,0.00008408282,0.9971988,0.0006467293,0.0001311767,0.00007525885,0.00002054576,0.0001159644,0.00009940693],"genre_scores_gemma":[0.8384523,0.00004750627,0.1606601,0.0005200378,0.00003781068,0.000003984961,0.00001046392,0.00001187971,0.0002558909],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.993876,"threshold_uncertainty_score":0.6988086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03876824261440971,"score_gpt":0.2969058658432672,"score_spread":0.2581376232288575,"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."}}