The University of Southampton
University of Southampton Institutional Repository

Universal learning curves of support vector machines

Record type: Article

Using methods of Statistical Physics, we investigate the role of model complexity in learning with support vector machines (SVMs), which are an important alternative to neural networks. We show the advantages of using SVMs with kernels of infinite complexity on noisy target rules, which, in contrast to common theoretical beliefs, are found to achieve optimal generalization error although the training error does not converge to the generalization error. Moreover, we find a universal asymptotics of the learning curves which only depend on the target rule but not on the SVM kernel.

Full text not available from this repository.

Citation

Opper, Manfred and Urbanczik, Robert (2001) Universal learning curves of support vector machines Physical Review Letters, 86, (19), pp. 4410-4413.

More information

Published date: 2001
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 259166
URI: http://eprints.soton.ac.uk/id/eprint/259166
PURE UUID: baeeb258-2b78-4987-85d3-0e94cdf609f7

Catalogue record

Date deposited: 14 Mar 2004
Last modified: 18 Jul 2017 09:25

Export record

Contributors

Author: Manfred Opper
Author: Robert Urbanczik

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×