Universal learning curves of support vector machines

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


Full text not available from this repository.


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: 259166
Date :
Date Event
Date Deposited: 14 Mar 2004
Last Modified: 27 Mar 2014 20:01
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/259166

Actions (login required)

View Item View Item