Statistical mechanics of support vector networks

Abstract

Using methods of Statistical Physics, we investigate the generalization performance of support vector machines (SVMs), which have been recently introduced as a general alternative to neural networks. For nonlinear classification rules, the generalization error saturates on a plateau, when the number of examples is too small to properly estimate the coefficients of the nonlinear part. When trained on simple rules, we find that SVMs overfit only weakly. The performance of SVMs is strongly enhanced, when the distribution of the inputs has a gap in feature space.

Publication DOI: https://doi.org/10.1103/PhysRevLett.82.2975
Divisions: Aston University (General)
Additional Information: Copyright of the American Physical Society
Uncontrolled Keywords: statistical physics,support vector machines,neural networks,nonlinear classification,generalization error
Publication ISSN: 1079-7114
Last Modified: 19 Mar 2024 08:09
Date Deposited: 10 Aug 2009 10:24
Full Text Link:
Related URLs: http://link.aps ... RevLett.82.2975 (Publisher URL)
PURE Output Type: Article
Published Date: 1999-04-05
Authors: Dietrich, Rainer
Opper, Manfred
Sompolinsky, Haim

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record