On the influence of the kernel on the generalization ability of support vector machines

by    I. Steinwart

Preprint series: 01-01 , Reports on Analysis and Computer Science

MSC:
68T10 Pattern recognition, speech recognition, {For cluster analysis, See 62H30}
CR: I.5.1.

Abstract: In this article we study the generalization abilities
of several classifiers of support vector machine type.
Our considerations are based on an investigation of
certain approximation properties of the used kernels
which also gives a new insight into the role of kernels
in these and other algorithms. For deterministic
supervisors we derive estimates on the generalization
performance which are asymptotically sharper than all
known results. Moreover, for supervisors which are
corrupted by a certain kind of noise we show that the
support vector approach yields acceptable generalization
results.

Keywords: Computational learning theory, pattern recognition, PAC model, maximal margin hyperplane, support vector machines, kernel methods

Upload: 2001-01-19


The author(s) agree, that this abstract may be stored as full text and distributed as such by abstracting services.