dc.contributor.author | Evgeniou, Theodoros | en_US |
dc.contributor.author | Pontil, Massimiliano | en_US |
dc.date.accessioned | 2004-10-20T21:04:34Z | |
dc.date.available | 2004-10-20T21:04:34Z | |
dc.date.issued | 1999-05-01 | en_US |
dc.identifier.other | AIM-1656 | en_US |
dc.identifier.other | CBCL-172 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/7262 | |
dc.description.abstract | This paper presents a computation of the $V_gamma$ dimension for regression in bounded subspaces of Reproducing Kernel Hilbert Spaces (RKHS) for the Support Vector Machine (SVM) regression $epsilon$-insensitive loss function, and general $L_p$ loss functions. Finiteness of the RV_gamma$ dimension is shown, which also proves uniform convergence in probability for regression machines in RKHS subspaces that use the $L_epsilon$ or general $L_p$ loss functions. This paper presenta a novel proof of this result also for the case that a bias is added to the functions in the RKHS. | en_US |
dc.format.extent | 1074347 bytes | |
dc.format.extent | 286742 bytes | |
dc.format.mimetype | application/postscript | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | AIM-1656 | en_US |
dc.relation.ispartofseries | CBCL-172 | en_US |
dc.title | On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces | en_US |