{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004632758,0.0002890652,0.00031895,0.0002415522,0.0001245678,0.0001671,0.00165924,0.0002683591,0.00009722907],"category_scores_gemma":[0.000112294,0.0003354289,0.0001475899,0.000639724,0.000155822,0.000570681,0.001776696,0.0004571198,0.00009859589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002459293,"about_ca_system_score_gemma":0.0004198528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004813812,"about_ca_topic_score_gemma":0.00023121,"domain_scores_codex":[0.997846,0.0002878816,0.0002397306,0.00113841,0.0001155778,0.0003724121],"domain_scores_gemma":[0.9982775,0.0001868501,0.0002208201,0.0009635644,0.0002259134,0.000125297],"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":[0.00001340394,0.00007095978,0.007015851,0.0000142092,0.00003640219,0.00006730431,0.0001763372,0.9092872,0.000007128641,0.08280186,0.0002739588,0.0002354139],"study_design_scores_gemma":[0.0002516226,0.00002648437,0.01866704,0.00004374991,0.00001521151,6.913011e-7,0.0000124446,0.917788,0.00003780846,0.06261221,0.0002131263,0.0003316362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01909319,0.00001888312,0.975224,0.0001616164,0.0007163626,0.0001926554,0.00001304063,0.0001137298,0.004466577],"genre_scores_gemma":[0.9679452,0.00005167362,0.03134878,0.0001149254,0.0001422421,0.000001257178,0.00001404729,0.000009444433,0.0003724545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.948852,"threshold_uncertainty_score":0.9999098,"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."}}