{"id":"W2768140828","doi":"10.1007/s10107-017-1209-5","title":"Robust multicategory support vector machines using difference convex algorithm","year":2017,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Division of Information and Intelligent Systems; National Science Foundation; National Institutes of Health; National Cancer Institute; Division of Mathematical Sciences; National Institute of General Medical Sciences","keywords":"Support vector machine; Outlier; Mathematics; Hinge loss; Consistency (knowledge bases); Algorithm; Generalization; Binary classification; Convex optimization; Mathematical optimization; Robustness (evolution); Artificial intelligence; Regular polygon; Machine learning; Computer science","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":[0.0001424868,0.0002409787,0.000337313,0.00005051563,0.0002950772,0.0003408345,0.0004052931,0.0001117016,0.00008717952],"category_scores_gemma":[0.0001178973,0.0002100777,0.00009195633,0.00003736245,0.0001787473,0.0001392604,0.000142339,0.0002287396,0.00005405763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003618501,"about_ca_system_score_gemma":0.00001083006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001981016,"about_ca_topic_score_gemma":0.000001756618,"domain_scores_codex":[0.9988717,0.00001636889,0.0002802852,0.000223559,0.0001994976,0.0004086208],"domain_scores_gemma":[0.9990252,0.00006894422,0.00007739853,0.0006559909,0.00004900724,0.0001234156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007646154,0.0002448364,0.0006221425,0.00043483,0.0001700938,0.0002079212,0.0006313031,0.0005317206,0.01759069,0.005808074,0.0002777053,0.973473],"study_design_scores_gemma":[0.0001837589,0.0000306751,0.0004682039,0.0001608955,0.00005020139,0.00005720418,0.00003313283,0.9815401,0.009276154,0.007329653,0.0005136557,0.0003563729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07583026,0.000084691,0.9190049,0.00004982845,0.0002587507,0.0003959803,0.000003943713,0.001434951,0.002936765],"genre_scores_gemma":[0.7112708,0.000004257912,0.288461,0.00001301802,0.0001040779,0.00002077147,0.000002903547,0.00004849278,0.00007466051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9810084,"threshold_uncertainty_score":0.856672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06823648029563915,"score_gpt":0.2859208472903247,"score_spread":0.2176843669946856,"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."}}