The University of Southampton
University of Southampton Institutional Repository

Universal learning curves of support vector machines

Universal learning curves of support vector machines
Universal learning curves of support vector machines
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.
4410-4413
Opper, Manfred
f7f8690a-fdcb-46f0-857d-c4140648039b
Urbanczik, Robert
372a5733-b60a-45b8-8c14-ecc05220d974
Opper, Manfred
f7f8690a-fdcb-46f0-857d-c4140648039b
Urbanczik, Robert
372a5733-b60a-45b8-8c14-ecc05220d974

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

Record type: Article

Abstract

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.

Text
papsvm.pdf - Other
Download (176kB)

More information

Published date: 2001
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 259184
URI: http://eprints.soton.ac.uk/id/eprint/259184
PURE UUID: feed7991-6ab8-46df-9fc4-763ef6e670b1

Catalogue record

Date deposited: 15 Mar 2004
Last modified: 14 Mar 2024 06:20

Export record

Contributors

Author: Manfred Opper
Author: Robert Urbanczik

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.

×