{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002407361,0.0001693334,0.0002575641,0.00006421576,0.0002951505,0.0001142954,0.0002094539,0.00006878801,0.00000288084],"category_scores_gemma":[0.00001516811,0.0001595321,0.00006034882,0.000288961,0.00004977476,0.00036739,0.000005972786,0.0004955953,5.171281e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000382174,"about_ca_system_score_gemma":0.00002832639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003181923,"about_ca_topic_score_gemma":0.000003148018,"domain_scores_codex":[0.9985507,0.0002920226,0.0003247412,0.0003745205,0.0002268234,0.0002312454],"domain_scores_gemma":[0.9992918,0.0001871872,0.0001965103,0.0001271254,0.00008209731,0.0001152505],"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":[0.00003150195,0.00002399523,0.00002455361,0.00003309324,0.00002261145,0.000005059289,0.002513428,0.9538489,0.003737831,0.0001934692,0.00001658004,0.039549],"study_design_scores_gemma":[0.0002837799,0.000323263,0.00003456807,0.00007592719,0.00001180071,0.00001567223,0.0001674024,0.9983006,0.0003889756,0.00002296791,0.0002224808,0.0001526039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004573699,0.0002996163,0.9937351,0.0004061083,0.0004755029,0.000224078,0.000002089047,0.0002617857,0.00002204276],"genre_scores_gemma":[0.9621374,0.00002114642,0.03750162,0.0001393613,0.0001389551,0.0000254096,0.000001691107,0.00001598486,0.00001840345],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9575638,"threshold_uncertainty_score":0.6505528,"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."}}