{"id":"W3117074306","doi":"10.1109/tnnls.2020.3045082","title":"Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Gradient descent; Generative grammar; Adversarial system; Langevin dynamics; Artificial intelligence; Training (meteorology); Computer science; Descent (aeronautics); Stochastic gradient descent; Mathematics; Applied mathematics; Statistical physics; Artificial neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001502586,0.001017772,0.0008636395,0.0003785715,0.0003912446,0.0006014463,0.001351795,0.0009877707,0.001055974],"category_scores_gemma":[0.003969818,0.0006332325,0.0006372766,0.0002848893,0.001194675,0.0007571006,0.001379122,0.001867067,0.0002994681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009678712,"about_ca_system_score_gemma":0.00129705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005298649,"about_ca_topic_score_gemma":0.006560174,"domain_scores_codex":[0.9995509,0.0001756623,0.00001832356,0.0001016201,0.0001043009,0.00004924155],"domain_scores_gemma":[0.9989083,0.0006818445,0.00009656796,0.0001036144,0.0001435287,0.00006613911],"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":[0.00002650043,0.00001481179,0.0005712718,0.00002047912,0.0000257023,0.00003662655,0.00003555645,0.9742559,0.001549458,0.01076392,0.0005489413,0.01215096],"study_design_scores_gemma":[0.00000168076,0.000003681015,0.00001657295,0.000001213152,9.517893e-7,0.000002824324,0.000001104962,0.9984195,0.0001512329,0.00134301,0.00005715234,0.000001171974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01647779,0.0001104358,0.9814854,0.0001521391,0.00002957883,0.00002732844,0.00002460173,0.0003499071,0.001342898],"genre_scores_gemma":[0.7852426,0.0002251157,0.2101863,0.0003387396,0.00005701869,0.0001867974,0.0002308867,0.0002547273,0.003277924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005298649,"threshold_uncertainty_score":0.0105356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03231864023372372,"score_gpt":0.2435596842701334,"score_spread":0.2112410440364097,"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."}}