{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T10:52:48Z","timestamp":1791197568567,"version":"4.1.0"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2015,1,5]],"date-time":"2015-01-05T00:00:00Z","timestamp":1420416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1055210"],"award-info":[{"award-number":["1055210"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1308960"],"award-info":[{"award-number":["1308960"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-CA149569"],"award-info":[{"award-number":["R01-CA149569"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P01-CA142538"],"award-info":[{"award-number":["P01-CA142538"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50-DA10075"],"award-info":[{"award-number":["P50-DA10075"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50-DA036107"],"award-info":[{"award-number":["P50-DA036107"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,1,1]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>The support vector machine (SVM) is a powerful binary classification tool with high accuracy and great flexibility. It has achieved great success, but its performance can be seriously impaired if many redundant covariates are included. Some efforts have been devoted to studying variable selection for SVMs, but asymptotic properties, such as variable selection consistency, are largely unknown when the number of predictors diverges to \u221e. We establish a unified theory for a general class of non-convex penalized SVMs. We first prove that, in ultrahigh dimensions, there is one local minimizer to the objective function of non-convex penalized SVMs having the desired oracle property. We further address the problem of non-unique local minimizers by showing that the local linear approximation algorithm is guaranteed to converge to the oracle estimator even in the ultrahigh dimensional setting if an appropriate initial estimator is available. This condition on the initial estimator is verified to be automatically valid as long as the dimensions are moderately high. Numerical examples provide supportive evidence.<\/jats:p>","DOI":"10.1111\/rssb.12100","type":"journal-article","created":{"date-parts":[[2015,1,5]],"date-time":"2015-01-05T05:35:25Z","timestamp":1420436125000},"page":"53-76","source":"Crossref","is-referenced-by-count":69,"title":["Variable Selection for Support Vector Machines in Moderately High Dimensions"],"prefix":"10.1093","volume":"78","author":[{"given":"Xiang","family":"Zhang","sequence":"first","affiliation":[{"name":"North Carolina State University , Raleigh , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Wu","sequence":"additional","affiliation":[{"name":"North Carolina State University , Raleigh , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Minnesota , Minneapolis , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Li","sequence":"additional","affiliation":[{"name":"Pennsylvania State University , University Park , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2015,1,5]]},"reference":[{"key":"2023021709312925000_rssb12100-cit-0001","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10479-004-5022-1","article-title":"The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems","volume":"133","author":"An","year":"2005","journal-title":"Ann. Ops Res."},{"key":"2023021709312925000_rssb12100-cit-0002","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1198\/016214505000000907","article-title":"Convexity, classification and risk bounds","volume":"101","author":"Bartlett","year":"2006","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0003","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-12-138","article-title":"Elastic scad as a novel penalization method for svm classification tasks in high-dimensional data","volume":"12","author":"Becker","year":"2011","journal-title":"BMC Bioinform."},{"key":"2023021709312925000_rssb12100-cit-0004","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1214\/08-AOS620","article-title":"Simultaneous analysis of Lasso and Dantzig selector","volume":"37","author":"Bickel","year":"2009","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0005","first-page":"82","volume-title":"Proc. 15th Int. Conf. Machine Learning","author":"Bradley","year":"1998"},{"key":"2023021709312925000_rssb12100-cit-0006","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-20192-9","volume-title":"Statistics for High-dimensional Data: Methods, Theory and Applications","author":"B\u00fchlmann","year":"2011"},{"key":"2023021709312925000_rssb12100-cit-0007","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1198\/jasa.2011.tm11199","article-title":"A direct estimation approach to sparse linear discriminant analysis","volume":"106","author":"Cai","year":"2011","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0008","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1093\/biomet\/asn034","article-title":"Extended bayesian information criteria for model selection with large model spaces","volume":"95","author":"Chen","year":"2008","journal-title":"Biometrika"},{"key":"2023021709312925000_rssb12100-cit-0009","first-page":"541","article-title":"An information criterion for variable selection in support vector machines","volume":"9","author":"Claeskens","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2023021709312925000_rssb12100-cit-0010","first-page":"1","volume-title":"Math Challenges Lecture","author":"Donoho","year":"2000"},{"key":"2023021709312925000_rssb12100-cit-0011","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1214\/07-AOS504","article-title":"High dimensional classification using features annealed independence rules","volume":"36","author":"Fan","year":"2008","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0012","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan","year":"2001","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0013","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1111\/j.1467-9868.2008.00674.x","article-title":"Sure independence screening for ultrahigh dimensional feature space (with discussion)","volume":"70","author":"Fan","year":"2008","journal-title":"J. R. Statist. Soc. B"},{"key":"2023021709312925000_rssb12100-cit-0014","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1214\/13-AOS1198","article-title":"Strong oracle optimality of folded concave penalized estimation","volume":"42","author":"Fan","year":"2014","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0015","volume-title":"The Elements of Statistical Learning","author":"Friedman","year":"2001"},{"key":"2023021709312925000_rssb12100-cit-0016","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"2023021709312925000_rssb12100-cit-0017","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1198\/016214508000001066","article-title":"Smoothly clipped absolute deviation on high dimensions","volume":"103","author":"Kim","year":"2008","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0018","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1093\/biomet\/asr084","article-title":"Global optimality of nonconvex penalized estimators","volume":"99","author":"Kim","year":"2012","journal-title":"Biometrika"},{"key":"2023021709312925000_rssb12100-cit-0019","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511754098","volume-title":"Quantile Regression","author":"Koenker","year":"2005"},{"key":"2023021709312925000_rssb12100-cit-0020","first-page":"1343","article-title":"A Bahadur representation of the linear support vector machine","volume":"9","author":"Koo","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2023021709312925000_rssb12100-cit-0021","volume-title":"Some asymptotic properties of the support vector machine","author":"Lin","year":"2000"},{"key":"2023021709312925000_rssb12100-cit-0022","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1015469627679","article-title":"Support vector machines and the bayes rule in classification","volume":"6","author":"Lin","year":"2002","journal-title":"Data Minng Knowl. Discov."},{"key":"2023021709312925000_rssb12100-cit-0023","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1023\/A:1012406528296","article-title":"Support vector machines for classification in nonstandard situations","volume":"46","author":"Lin","year":"2002","journal-title":"Mach. Learn."},{"key":"2023021709312925000_rssb12100-cit-0024","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1198\/jasa.2011.tm09738","article-title":"Sparsenet: coordinate descent with nonconvex penalties","volume":"106","author":"Mazumder","year":"2011","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0025","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1214\/009053606000000281","article-title":"High-dimensional graphs and variable selection with the lasso","volume":"34","author":"Meinshausen","year":"2006","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0026","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1214\/07-AOS582","article-title":"Lasso-type recovery of sparse representations for high-dimensional data","volume":"37","author":"Meinshausen","year":"2009","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0027","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1016\/j.jspi.2012.03.002","article-title":"Oracle properties of scad-penalized support vector machine","volume":"142","author":"Park","year":"2012","journal-title":"J. Statist. Planng Inf."},{"key":"2023021709312925000_rssb12100-cit-0028","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"1978","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0029","first-page":"289","article-title":"Convex analysis approach to D.C. programming: theory, algorithms and applications","volume":"22","author":"Tao","year":"1997","journal-title":"Acta Math. Vietnam."},{"key":"2023021709312925000_rssb12100-cit-0030","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Statist. Soc. B"},{"key":"2023021709312925000_rssb12100-cit-0031","volume-title":"The Nature of Statistical Learning Theory","author":"Vapnik","year":"1996"},{"key":"2023021709312925000_rssb12100-cit-0032","doi-asserted-by":"crossref","first-page":"2505","DOI":"10.1214\/13-AOS1159","article-title":"Calibrating non-convex penalized regression in ultra-high dimension","volume":"41","author":"Wang","year":"2013","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0033","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1080\/01621459.2012.656014","article-title":"Quantile regression for analyzing heterogeneity in ultra-high dimension","volume":"107","author":"Wang","year":"2012","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0034","first-page":"589","article-title":"The doubly regularized support vector machine","volume":"16","author":"Wang","year":"2006","journal-title":"Statist. Sin."},{"key":"2023021709312925000_rssb12100-cit-0035","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1093\/bioinformatics\/btm579","article-title":"Hybrid huberized support vector machines for microarray classification and gene selection","volume":"24","author":"Wang","year":"2008","journal-title":"Bioinformatics"},{"key":"2023021709312925000_rssb12100-cit-0036","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.3150\/10-BEJ320","article-title":"Support vector machines with a reject option","volume":"17","author":"Wegkamp","year":"2011","journal-title":"Bernoulli"},{"key":"2023021709312925000_rssb12100-cit-0037","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1214\/aos\/1176347021","article-title":"On m-processes and m-estimation","volume":"17","author":"Welsh","year":"1989","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0038","first-page":"2261","article-title":"High dimensional inverse covariance matrix estimation via linear programming","volume":"99","author":"Yuan","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"2023021709312925000_rssb12100-cit-0040","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1214\/09-AOS729","article-title":"Nearly unbiased variable selection under minimax concave penalty","volume":"38","author":"Zhang","year":"2010","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0039","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1093\/bioinformatics\/bti736","article-title":"Gene selection using support vector machines with non-convex penalty","volume":"22","author":"Zhang","year":"2006","journal-title":"Bioinformatics"},{"key":"2023021709312925000_rssb12100-cit-0041","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1214\/07-AOS520","article-title":"The sparsity and bias of the lasso selection in high-dimensional linear regression","volume":"36","author":"Zhang","year":"2008","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0042","first-page":"2541","article-title":"On model selection consistency of lasso","volume":"7","author":"Zhao","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"2023021709312925000_rssb12100-cit-0043","first-page":"49","article-title":"1-norm support vector machines","volume":"16","author":"Zhu","year":"2004","journal-title":"Adv. Neur. Inform. Process. Syst."},{"key":"2023021709312925000_rssb12100-cit-0044","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1198\/016214506000000735","article-title":"The adaptive lasso and its oracle properties","volume":"101","author":"Zou","year":"2006","journal-title":"J. Am. Statist. Ass."},{"key":"2023021709312925000_rssb12100-cit-0045","first-page":"675","article-title":"An improved 1-norm svm for simultaneous classification and variable selection","author":"Zou","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"2023021709312925000_rssb12100-cit-0046","first-page":"1509","article-title":"One-step sparse estimates in nonconcave penalized likelihood models","volume":"36","author":"Zou","year":"2008","journal-title":"Ann. Statist."},{"key":"2023021709312925000_rssb12100-cit-0047","first-page":"379","article-title":"The f-infinity norm support vector machine","volume":"18","author":"Zou","year":"2008","journal-title":"Statist. Sin."}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/78\/1\/53\/49235734\/jrsssb_78_1_53.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/78\/1\/53\/49235734\/jrsssb_78_1_53.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T07:49:08Z","timestamp":1717660148000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/78\/1\/53\/7040655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,5]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2015,1,5]]},"published-print":{"date-parts":[[2016,1,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12100","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2016,1]]},"published":{"date-parts":[[2015,1,5]]}}}