From Regression to Classification in Support Vector Machines
dc.contributor.author | Pontil, Massimiliano | en_US |
dc.contributor.author | Rifkin, Ryan | en_US |
dc.contributor.author | Evgeniou, Theodoros | en_US |
dc.date.accessioned | 2004-10-20T21:04:26Z | |
dc.date.available | 2004-10-20T21:04:26Z | |
dc.date.issued | 1998-11-01 | en_US |
dc.identifier.other | AIM-1649 | en_US |
dc.identifier.other | CBCL-166 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/7258 | |
dc.description.abstract | We study the relation between support vector machines (SVMs) for regression (SVMR) and SVM for classification (SVMC). We show that for a given SVMC solution there exists a SVMR solution which is equivalent for a certain choice of the parameters. In particular our result is that for $epsilon$ sufficiently close to one, the optimal hyperplane and threshold for the SVMC problem with regularization parameter C_c are equal to (1-epsilon)^{- 1} times the optimal hyperplane and threshold for SVMR with regularization parameter C_r = (1-epsilon)C_c. A direct consequence of this result is that SVMC can be seen as a special case of SVMR. | en_US |
dc.format.extent | 807016 bytes | |
dc.format.extent | 194881 bytes | |
dc.format.mimetype | application/postscript | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | AIM-1649 | en_US |
dc.relation.ispartofseries | CBCL-166 | en_US |
dc.title | From Regression to Classification in Support Vector Machines | en_US |