Learning with Rigorous Support Vector Machines
We examine the so-called rigorous support vector machine (RSVM)
approach proposed by Vapnik (1998). The formulation of RSVM is derived by
explicitly implementing the structural risk minimization principle
with a parameter H used to directly control the VC dimension of
the set of separating hyperplanes. By optimizing the dual problem,
RSVM finds the optimal separating hyperplane from a set of
functions with VC dimension approximate to H^2+1. RSVM produces
classifiers equivalent to those obtained by classic SVMs for
appropriate parameter choices, but the use of the parameter H
facilitates model selection, thus minimizing VC bounds on the
generalization risk more effectively. In our empirical studies, good
models are achieved for an appropriate
H^2 in [5% L, 30% L] where L is the size of
Rensselaer Polytechnic Institute
Vladimir N. Vapnik
NEC Labs America, Inc.
The RSVM package written in C++
Welcome any bug report and appreciate it if someone could implement a more
efficient solver for RSVM and inform me of that. This paper has
been accepted by COLT 2003.
Contact Jinbo Bi (email@example.com) for information about this page.