Universal learning curves of support vector machines

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


[img] PDF
Download (172Kb)


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.

Item Type: Article
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259184
Date Deposited: 15 Mar 2004
Last Modified: 27 Mar 2014 20:01
Further Information:Google Scholar
ISI Citation Count:19
URI: http://eprints.soton.ac.uk/id/eprint/259184

Actions (login required)

View Item View Item

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