On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7262

Full metadata record

DC Field	Value	Language
dc.creator	Evgeniou, Theodoros	-
dc.creator	Pontil, Massimiliano	-
dc.date	2004-10-20T21:04:34Z	-
dc.date	2004-10-20T21:04:34Z	-
dc.date	1999-05-01	-
dc.date.accessioned	2013-10-09T02:48:50Z	-
dc.date.available	2013-10-09T02:48:50Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1656	-
dc.identifier	CBCL-172	-
dc.identifier	http://hdl.handle.net/1721.1/7262	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	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.	-
dc.format	1074347 bytes	-
dc.format	286742 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1656	-
dc.relation	CBCL-172	-
dc.title	On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI