{"id":"W2784067649","doi":"10.48550/arxiv.1801.03558","title":"Inference Suboptimality in Variational Autoencoders","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Imperfect; Divergence (linguistics); Approximate inference; Computer science; Latent variable; Artificial intelligence; Artificial neural network; Generator (circuit theory); Algorithm; Machine learning; Mathematics; Applied mathematics; Pattern recognition (psychology); Power (physics); Physics","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":[0.008704798,0.001525019,0.00238774,0.001045197,0.001055199,0.002593208,0.002178137,0.002632446,0.002813056],"category_scores_gemma":[0.04215754,0.001741508,0.001576307,0.001028837,0.004328157,0.004381128,0.003728959,0.005413787,0.0003985311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003875921,"about_ca_system_score_gemma":0.002430835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009203646,"about_ca_topic_score_gemma":0.008761678,"domain_scores_codex":[0.9956563,0.002349067,0.0002324331,0.0009465567,0.0005571768,0.0002585749],"domain_scores_gemma":[0.9634654,0.03310542,0.0008214375,0.001437452,0.0008297783,0.0003405355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000952343,0.00003120259,0.00111118,0.0001598855,0.0001106123,0.0001333572,0.0001653721,0.7518654,0.0007416215,0.2306743,0.001993012,0.01291874],"study_design_scores_gemma":[0.000009309708,0.000006110132,0.00006784842,0.00001466627,0.000005708233,0.00001360689,0.000007817796,0.8647215,0.0002192182,0.1346953,0.0002323065,0.000006610348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01552895,0.0005668481,0.9798954,0.001219896,0.00005329569,0.0000309857,0.0001261073,0.0002554315,0.002323073],"genre_scores_gemma":[0.7041584,0.001172562,0.2857906,0.001196187,0.0003026172,0.0003483227,0.0007239315,0.000554665,0.005752836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009203646,"threshold_uncertainty_score":0.04603589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07834561634935609,"score_gpt":0.2028202500474214,"score_spread":0.1244746336980653,"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."}}