{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001855673,0.0001085612,0.0001391789,0.0000442123,0.0001738799,0.000017056,0.000422882,0.0000349566,0.00004093074],"category_scores_gemma":[0.00001181507,0.00007747757,0.00003769695,0.0004035412,0.0003811395,0.0002564812,0.00004506352,0.00007220208,0.000002640997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001012782,"about_ca_system_score_gemma":0.00004799713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001985977,"about_ca_topic_score_gemma":0.00002607376,"domain_scores_codex":[0.9992875,0.00007083997,0.00008011355,0.0003318163,0.00006014426,0.0001695327],"domain_scores_gemma":[0.9993145,0.0001146676,0.00007244324,0.0003386729,0.0001016859,0.00005805873],"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":[0.0003633224,0.00008895971,0.001643794,0.00001339422,0.0001522436,0.00008843316,0.002734482,0.5970274,0.002013172,0.3944083,0.0001648747,0.001301589],"study_design_scores_gemma":[0.0004942098,0.0002907906,0.002161075,0.000033481,0.00002947223,0.000004859995,0.0003475591,0.992087,0.003565308,0.0007556875,0.00007797538,0.0001525511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.431668,0.000002481682,0.567654,0.00009150838,0.00004817825,0.00005716679,9.437263e-7,0.00001518426,0.0004626131],"genre_scores_gemma":[0.9938159,0.000009375734,0.005812681,0.00005265308,0.00003434105,2.537041e-7,3.717258e-7,0.000005040309,0.0002693761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.562148,"threshold_uncertainty_score":0.3159444,"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."}}