{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002006357,0.0004587397,0.0005143375,0.0002157868,0.0001768053,0.0002429836,0.002216927,0.0002873193,0.0001615296],"category_scores_gemma":[0.00004242896,0.0004961808,0.0004007085,0.0004520314,0.0001146302,0.0004619017,0.002778715,0.0006766038,0.0004535179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005470841,"about_ca_system_score_gemma":0.0002672411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002199115,"about_ca_topic_score_gemma":0.0001548078,"domain_scores_codex":[0.9970415,0.0002918321,0.0002051855,0.001834136,0.00014218,0.0004852005],"domain_scores_gemma":[0.997295,0.0001658702,0.0002864326,0.001733147,0.000308578,0.0002109808],"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":[0.00007607909,0.0002124166,0.001820226,0.00002835143,0.0004916833,0.0004966023,0.001345627,0.8687763,0.00009727164,0.1219049,0.003714971,0.001035504],"study_design_scores_gemma":[0.0005489744,0.0000629374,0.002676927,0.00008663013,0.0001040128,0.000002025172,0.0003783562,0.8403693,0.0002485468,0.1532447,0.001575836,0.0007016625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04128548,0.0002502619,0.9467496,0.0004221793,0.00173422,0.0004406811,0.00006932915,0.0001797203,0.008868492],"genre_scores_gemma":[0.9907719,0.0001885621,0.006385354,0.0001829455,0.0002633257,0.000001425596,0.00002409601,0.00002460819,0.002157782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9494864,"threshold_uncertainty_score":0.999749,"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."}}