A Note on the Generalization Performance of Kernel Classifiers with Margin

Authors: Theodoros Evgeniou and Massimiliano Pontil .

Source: Lecture Notes in Artificial Intelligence Vol. 1968, 2000, 306 - 315.

Abstract. We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the Vgamma dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.

©Copyright 2000 Springer