Statistical Mechanics of Support Vector Networks
Disordered Systems and Neural Networks
2009-10-31 v2
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.
Keywords
Cite
@article{arxiv.cond-mat/9811421,
title = {Statistical Mechanics of Support Vector Networks},
author = {Rainer Dietrich and Manfred Opper and Haim Sompolinsky},
journal= {arXiv preprint arXiv:cond-mat/9811421},
year = {2009}
}
Comments
REVTeX, 4 pages, 2 figures, accepted by Phys. Rev. Lett (typos corrected)