{"id":"W2949593890","doi":"","title":"Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations.","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Exponential family; Simple (philosophy); Inference; Applied mathematics; Gradient descent; Approximations of π; Mathematics; Convergence (economics); Representation (politics); Exponential function; Bayesian inference; Approximate inference; Computer science; Algorithm; Mathematical optimization; Bayesian probability; Artificial neural network; Artificial intelligence; Mathematical analysis; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003735239,0.00109658,0.0008674617,0.0008290479,0.0005838625,0.001176285,0.00233355,0.00173305,0.003776854],"category_scores_gemma":[0.0188251,0.0008489948,0.001037781,0.0006889251,0.001224495,0.003145836,0.002079709,0.002650496,0.00166684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169517,"about_ca_system_score_gemma":0.001852427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006173844,"about_ca_topic_score_gemma":0.009644754,"domain_scores_codex":[0.9986558,0.0007505649,0.00006168237,0.0002045481,0.0002637071,0.00006367789],"domain_scores_gemma":[0.9965606,0.002347172,0.0001944496,0.0003908593,0.0003812643,0.0001256285],"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":[0.0003199581,0.0001569374,0.002253509,0.0004106557,0.0002421221,0.0001616503,0.0003518788,0.5430661,0.005016035,0.2202707,0.01114939,0.216601],"study_design_scores_gemma":[0.000008426411,0.00000996259,0.00007910488,0.00001310986,0.000005999315,0.00003095255,0.000007482678,0.9764193,0.000564399,0.02138419,0.001467891,0.000009170645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002148701,0.000176178,0.9965318,0.00009092156,0.00002703644,0.00003822525,0.00003487865,0.0002851716,0.0006669454],"genre_scores_gemma":[0.1247873,0.00027502,0.870053,0.0002177173,0.00006212309,0.0001941653,0.0003666453,0.0003817383,0.003662357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006173844,"threshold_uncertainty_score":0.01975411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009866456545828465,"score_gpt":0.2452224025964696,"score_spread":0.2353559460506412,"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."}}