{"id":"W2803117117","doi":"10.48550/arxiv.1802.08249","title":"On the Convergence and Robustness of Training GANs with Regularized Optimal Transport","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Robustness (evolution); Mathematical optimization; Wasserstein metric; Computer science; Discriminator; Convergence (economics); Metric (unit); Algorithm; Probability distribution; Mathematics; Artificial intelligence; Deep learning; Applied mathematics","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":[0.004365631,0.001580418,0.001314937,0.0009372629,0.0005672059,0.001070079,0.001614929,0.00171376,0.002193728],"category_scores_gemma":[0.01994476,0.0007978916,0.0008935236,0.0005394745,0.001919004,0.001978402,0.002047711,0.00295434,0.0005483742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001834415,"about_ca_system_score_gemma":0.001203775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005767759,"about_ca_topic_score_gemma":0.004748892,"domain_scores_codex":[0.998936,0.0005007074,0.00005002494,0.00020789,0.0001941643,0.0001112006],"domain_scores_gemma":[0.9916207,0.006877449,0.0003469182,0.0004833129,0.0004581983,0.0002134899],"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":[0.0001228731,0.00003035478,0.0007466222,0.00004293265,0.00003599841,0.00004427982,0.00004957213,0.9694467,0.00114135,0.01397486,0.0007795113,0.01358493],"study_design_scores_gemma":[0.000005324072,0.00001148911,0.00005188606,0.000005827615,0.000002574575,0.000007613992,0.000003184532,0.9951998,0.0003049193,0.004326515,0.00007853525,0.00000227695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07826582,0.0008853899,0.9123787,0.0008640406,0.00007828638,0.0000853176,0.0001121958,0.001313033,0.006017187],"genre_scores_gemma":[0.8498493,0.0005632988,0.1436161,0.0004921034,0.000103069,0.0002058367,0.0004400371,0.0006124098,0.00411796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005767759,"threshold_uncertainty_score":0.02308798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05172647181330694,"score_gpt":0.1591584771837795,"score_spread":0.1074320053704726,"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."}}