{"id":"W2970370162","doi":"","title":"Reducing Noise in GAN Training with Variance Reduced Extragradient","year":2019,"lang":"en","type":"article","venue":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Hasler Stiftung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"MNIST database; Convergence (economics); Variance (accounting); Computer science; Noise (video); Mathematical optimization; Class (philosophy); Training (meteorology); Generative grammar; Artificial intelligence; Algorithm; Machine learning; Mathematics; Deep learning; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002278218,0.001213961,0.001111878,0.0003682368,0.0003347659,0.0006935241,0.001173103,0.001315104,0.001656179],"category_scores_gemma":[0.01055881,0.0005870613,0.0005051882,0.0002898213,0.001028501,0.001204985,0.001426247,0.002312607,0.0005515247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008075221,"about_ca_system_score_gemma":0.0008734167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002624952,"about_ca_topic_score_gemma":0.003681832,"domain_scores_codex":[0.9990767,0.0004504116,0.00003617094,0.0001426105,0.0002118281,0.00008210111],"domain_scores_gemma":[0.9968295,0.002444048,0.0001446383,0.0002360824,0.0002588717,0.00008693587],"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":[0.0001064606,0.00005107405,0.0005931548,0.0000538961,0.00003417354,0.0000840158,0.00005763428,0.9553928,0.003359538,0.01536248,0.00173119,0.02317352],"study_design_scores_gemma":[0.000004824091,0.00001436837,0.00003970099,0.000004060463,0.000001608143,0.00001103551,0.000002326593,0.9961126,0.0007448019,0.002861544,0.0002005522,0.000002547442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02602964,0.000350168,0.9700743,0.0003333534,0.00005515358,0.00004169818,0.0000456438,0.0007755506,0.002294398],"genre_scores_gemma":[0.7542014,0.0002741921,0.2398413,0.0005013249,0.00007178378,0.0001936699,0.0002456276,0.0004976264,0.004173043],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002624952,"threshold_uncertainty_score":0.01204854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01294171347193677,"score_gpt":0.2262014307785642,"score_spread":0.2132597173066275,"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."}}