Fast Rates for Support Vector Machines
Lists
Only you see this
Abstract
We establish learning rates to the Bayes risk for support vector machines (SVMs) using a regularization sequence ${\it \lambda}_{n}={\it n}^{-\rm \alpha}$ , where ${\it \alpha}\in$ (0,1) is arbitrary. Under a noise condition recently proposed by Tsybakov these rates can become faster than n − 1/2. In order to deal with the approximation error we present a general concept called the approximation error function which describes how well the infinite sample versions of the considered SVMs approximate the data-generating distribution. In addition we discuss in some detail the relation between the “classical” approximation error and the approximation error function. Finally, for distributions satisfying a geometric noise assumption we establish some learning rates when the used RKHS is a Sobolev space.
BibTeX
@inproceedings{steinwart2005fast,
author = {Ingo Steinwart and Clint Scovel},
title = {{Fast Rates for Support Vector Machines}},
booktitle = {Conference on Learning Theory},
year = {2005},
doi = {10.1007/11503415\_19},
}Loading related content...