{"id":"W4404506273","doi":"10.1016/j.jspi.2024.106250","title":"Estimation and group-feature selection in sparse mixture-of-experts with diverging number of parameters","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada; Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Feature selection; Group (periodic table); Selection (genetic algorithm); Statistics; Feature (linguistics); Estimation; Pattern recognition (psychology); Combinatorics; Artificial intelligence; Computer science","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":[0.0003104997,0.00007486736,0.0001933514,0.0001009534,0.00002115882,0.00006212628,0.00006719067,0.00004555384,0.000001556085],"category_scores_gemma":[0.0001161195,0.00005121656,0.0000122487,0.0001646019,0.00006032468,0.0003344008,0.00002375234,0.0001961489,6.803414e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001061507,"about_ca_system_score_gemma":0.00003734449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834385,"about_ca_topic_score_gemma":0.000001379094,"domain_scores_codex":[0.9993678,0.00006055575,0.0002165777,0.0001144037,0.0001511886,0.00008952062],"domain_scores_gemma":[0.9992726,0.0004781959,0.0001071952,0.00003628639,0.00004922902,0.00005647787],"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":[0.0001633919,0.00008023516,0.04432928,0.0004910635,0.00007228892,0.0002475269,0.005822864,0.001487489,0.002202963,0.2537537,0.0004417176,0.6909075],"study_design_scores_gemma":[0.0004145539,0.0006475755,0.0433066,0.002096562,0.00004024642,0.0006423244,0.0000555905,0.8415482,0.0007573441,0.1102881,0.00003548013,0.0001673622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1303128,0.0003859232,0.8690721,0.00008171963,0.00004971406,0.00002443747,0.000002566612,0.000004908729,0.00006583362],"genre_scores_gemma":[0.5464041,0.00002368844,0.45355,0.00001138426,0.00000639652,2.852236e-7,2.890613e-7,0.000001619494,0.00000231028],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8400607,"threshold_uncertainty_score":0.2088551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01710034288525405,"score_gpt":0.3144785818843017,"score_spread":0.2973782389990477,"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."}}