{"id":"W3107020245","doi":"10.48550/arxiv.1910.06922","title":"Gradient penalty from a maximum margin perspective","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Margin (machine learning); Hinge loss; Maximization; Norm (philosophy); Computer science; Mathematical optimization; Gradient method; Mathematics; Applied mathematics; Algorithm; Artificial intelligence; Law; Support vector machine; Machine learning","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":[0.001571898,0.001313121,0.0008618031,0.0005219131,0.0003853611,0.001143983,0.001473613,0.00169115,0.005538638],"category_scores_gemma":[0.005741755,0.000430483,0.0005007106,0.0004910892,0.001604855,0.002284885,0.001865814,0.00297827,0.001449722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009396269,"about_ca_system_score_gemma":0.0007169023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006877996,"about_ca_topic_score_gemma":0.0008653447,"domain_scores_codex":[0.9991273,0.0003040334,0.00003948112,0.0001834034,0.0002786877,0.00006715771],"domain_scores_gemma":[0.998759,0.0007143116,0.00009767248,0.0001986064,0.0001548289,0.00007562171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001437599,0.00006879374,0.0005442668,0.0001823886,0.00004961808,0.0001548366,0.0001005124,0.6290928,0.01250629,0.2588864,0.009470684,0.08879964],"study_design_scores_gemma":[0.00001307576,0.0000503327,0.0001205264,0.00002426148,0.000008320255,0.0001009449,0.000007671084,0.9081367,0.004023691,0.08198474,0.005517069,0.0000127125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004849205,0.0002226803,0.9873985,0.0005818893,0.00006490912,0.00002888122,0.00005935562,0.0004422516,0.006352325],"genre_scores_gemma":[0.5838495,0.0008171599,0.3896086,0.001152203,0.0002980641,0.000327207,0.0003936493,0.001049008,0.02250456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005538638,"threshold_uncertainty_score":0.01852858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05205662847975387,"score_gpt":0.1800130994366128,"score_spread":0.127956470956859,"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."}}