{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:21Z","timestamp":1760245041226,"version":"3.41.0"},"reference-count":34,"publisher":"MIT Press","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2017,12]]},"abstract":"<jats:p>This letter aims at refined error analysis for binary classification using support vector machine (SVM) with gaussian kernel and convex loss. Our first result shows that for some loss functions, such as the truncated quadratic loss and quadratic loss, SVM with gaussian kernel can reach the almost optimal learning rate provided the regression function is smooth. Our second result shows that for a large number of loss functions, under some Tsybakov noise assumption, if the regression function is infinitely smooth, then SVM with gaussian kernel can achieve the learning rate of order [Formula: see text], where [Formula: see text] is the number of samples.<\/jats:p>","DOI":"10.1162\/neco_a_00968","type":"journal-article","created":{"date-parts":[[2017,4,14]],"date-time":"2017-04-14T18:47:22Z","timestamp":1492195642000},"page":"3353-3380","source":"Crossref","is-referenced-by-count":8,"title":["Learning Rates for Classification with Gaussian Kernels"],"prefix":"10.1162","volume":"29","author":[{"given":"Shao-Bo","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Statistics, Wenzhou University, Wenzhou 325035, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinshan","family":"Zeng","sequence":"additional","affiliation":[{"name":"College of Computer Information Engineering, Jiangxi Normal University, Nanchang, 330022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Management, Xi'an Jiaotong University, Xi'an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1214\/009053607000000839"},{"key":"B3","first-page":"1143","volume":"5","author":"Chen D. R.","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618796"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1214\/12-EJS760"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1142\/S0219530511001923"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321891855"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS825"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2011.01.005"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2336665"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00641"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-009-9080-0"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2012.05.001"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2011.01.001"},{"key":"B15","first-page":"67","volume":"2","author":"Steinwart I.","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","volume-title":"Support vector machines","author":"Steinwart I.","year":"2008"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.881713"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000001226"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00794"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2008.05.008"},{"key":"B21","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1214\/009053604000000869","volume":"32","author":"Tsybakov A.","year":"2004","journal-title":"Ann. Statis."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/b95439"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jco.2006.06.007"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053491896"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s11425-010-4043-2"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2010.11.016"},{"key":"B27","first-page":"1447","volume":"10","author":"Xiang D. H.","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/18.796368"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-007-9049-0"},{"key":"B30","first-page":"249","volume":"8","author":"Ying Y. M.","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1006\/jcom.2002.0635"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.813564"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-004-7206-2"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_00968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:29:48Z","timestamp":1750199388000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/29\/12\/3353-3380\/8324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":34,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["10.1162\/neco_a_00968"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00968","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"type":"print","value":"0899-7667"},{"type":"electronic","value":"1530-888X"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}