{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001223455,0.0003216543,0.0003894251,0.0003604941,0.0001961775,0.0003271867,0.001557171,0.0001426914,0.00004930012],"category_scores_gemma":[0.0001117652,0.0002974143,0.00008290131,0.001736581,0.0001788644,0.001605528,0.0001933268,0.0004089839,0.0000380116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002191746,"about_ca_system_score_gemma":0.0004891599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00036258,"about_ca_topic_score_gemma":0.0001180819,"domain_scores_codex":[0.9969452,0.0001667885,0.0004614237,0.0009405353,0.0004286393,0.001057417],"domain_scores_gemma":[0.9983043,0.0001445209,0.000230638,0.0009773062,0.00009728949,0.0002459126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001091563,0.0003855066,0.01092861,0.00007003571,0.00003124521,0.0002554096,0.01200309,0.1519604,0.689923,0.03065909,0.0008651895,0.1028092],"study_design_scores_gemma":[0.001209031,0.0009344958,0.02794274,0.0009783659,0.00001339718,0.0002272401,0.0005774802,0.6478087,0.3127058,0.00251224,0.003559296,0.001531187],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2407355,0.00008065951,0.7450726,0.001108977,0.000451025,0.0008675842,0.000003884466,0.0003348462,0.01134496],"genre_scores_gemma":[0.8405013,0.00002176412,0.1581317,0.0005529509,0.00007847032,0.000115979,0.000001299654,0.00001947666,0.0005771026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5997658,"threshold_uncertainty_score":0.9999478,"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."}}