UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

A note on the generalization performance of kernel classifiers with margin

Evgeniou, T; Pontil, M; (2000) A note on the generalization performance of kernel classifiers with margin. In: Arimura, H and Jain, S and Sharma, A, (eds.) ALGORITHMIC LEARNING THEORY, PROCEEDINGS. (pp. 306 - 315). SPRINGER-VERLAG BERLIN

Full text not available from this repository.

Abstract

We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stern out of this class of machines. The bounds are derived through computations of the V-gamma 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.

Type:Proceedings paper
Title:A note on the generalization performance of kernel classifiers with margin
Event:11th International Conference on Algorithmic Learning Theory (ALT 2000)
Location:SYDNEY, AUSTRALIA
Dates:2000-12-11 - 2000-12-13
ISBN:3-540-41237-9
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record