{"id":"W3017843993","doi":"10.48550/arxiv.2004.10495","title":"Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regularization (linguistics); Langevin dynamics; Gradient descent; Inference; Stability (learning theory); Mathematical optimization; Generative grammar; Artificial intelligence; Algorithm; Statistical physics; Machine learning; Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003457456,0.0003976517,0.0005823312,0.0001792588,0.0001794045,0.00009887305,0.001257486,0.0002266616,0.00005482566],"category_scores_gemma":[0.00008982128,0.0004462842,0.0003210414,0.0005301968,0.0001237282,0.0003973471,0.001444002,0.000485371,0.00001667905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002687914,"about_ca_system_score_gemma":0.000434299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002077481,"about_ca_topic_score_gemma":0.00007316036,"domain_scores_codex":[0.9973623,0.0004521107,0.0003883161,0.001191604,0.0002066188,0.0003990206],"domain_scores_gemma":[0.9981197,0.0001944328,0.0005000839,0.0006869364,0.0002705008,0.0002284217],"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":[0.00007222858,0.000117827,0.0003046099,0.00005200951,0.0003128661,0.0001161636,0.003193543,0.928,0.002138074,0.06263296,0.0003474126,0.002712298],"study_design_scores_gemma":[0.0006471667,0.0001137916,0.0007744576,0.00008046755,0.00009891065,0.000001866217,0.0002053927,0.9801323,0.001535652,0.01555563,0.0003982604,0.0004561046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01853997,0.00007869465,0.978523,0.0004376522,0.001110127,0.0004005805,0.00004736537,0.0001024435,0.0007601334],"genre_scores_gemma":[0.9621122,0.00004901193,0.03720337,0.0001448179,0.0003450329,0.000001954868,0.0000423794,0.00002111275,0.00008008966],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9435723,"threshold_uncertainty_score":0.9997989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1202132709674541,"score_gpt":0.1922385612910626,"score_spread":0.07202529032360847,"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."}}