Paper on generalization bounds for the support vector method

[YORAM Gat]

The following paper is now available at

http://www.stat.Berkeley.EDU/tech-reports/548.ps.Z


A bound concerning the generalization ability of a certain class of
learning algorithms

Yoram Gat

Abstract:
A classifier is said to have good generalization ability if it
performs on test data almost as well as it does on the training data.
The main result of this paper provides a sufficient condition for
a learning algorithm to have good finite sample generalization ability.
This criterion applies in some cases where the set of all possible
classifiers has infinite VC dimension. We apply the result to prove
the good generalization ability of support vector machines.