On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces
dc.date.accessioned | 2004-10-20T21:04:34Z | |
dc.date.accessioned | 2018-11-24T10:23:35Z | |
dc.date.available | 2004-10-20T21:04:34Z | |
dc.date.available | 2018-11-24T10:23:35Z | |
dc.date.issued | 1999-05-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/7262 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/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.language.iso | en_US | |
dc.title | On the V(subscript gamma) Dimension for Regression in Reproducing Kernel Hilbert Spaces | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1656.pdf | 286.7Kb | application/pdf | View/ |
AIM-1656.ps | 1.074Mb | application/postscript | View/ |