nips nips2004 nips2004-69 nips2004-69-reference knowledge-graph by maker-knowledge-mining

69 nips-2004-Fast Rates to Bayes for Kernel Machines


Source: pdf

Author: Ingo Steinwart, Clint Scovel

Abstract: We establish learning rates to the Bayes risk for support vector machines (SVMs) with hinge loss. In particular, for SVMs with Gaussian RBF kernels we propose a geometric condition for distributions which can be used to determine approximation properties of these kernels. Finally, we compare our methods with a recent paper of G. Blanchard et al.. 1


reference text

[1] I. Steinwart. Support vector machines are universally consistent. J. Complexity, 18:768–791, 2002.

[2] T. Zhang. Statistical behaviour and consistency of classification methods based on convex risk minimization. Ann. Statist., 32:56–134, 2004.

[3] I. Steinwart. Consistency of support vector machines and other regularized kernel machines. IEEE Trans. Inform. Theory, to appear, 2005.

[4] L. Devroye, L. Gy¨ rfi, and G. Lugosi. A Probabilistic Theory of Pattern Recognition. o Springer, New York, 1996.

[5] A.B. Tsybakov. Optimal aggregation of classifiers in statistical learning. Ann. Statist., 32:135–166, 2004.

[6] Y. Yang. Minimax nonparametric classification—part I and II. IEEE Trans. Inform. Theory, 45:2271–2292, 1999.

[7] N. Cristianini and J. Shawe-Taylor. An Introduction to Support Vector Machines. Cambridge University Press, 2000.

[8] I. Steinwart. On the influence of the kernel on the consistency of support vector machines. J. Mach. Learn. Res., 2:67–93, 2001.

[9] Q. Wu and D.-X. Zhou. Analysis of support vector machine classification. Tech. Report, City University of Hong Kong, 2003.

[10] C. Scovel and I. Steinwart. Fast rates for support vector machines. Ann. Statist., submitted, 2003. http://www.c3.lanl.gov/˜ingo/publications/ ann-03.ps.

[11] G. Blanchard, O. Bousquet, and P. Massart. Statistical performance of support vector machines. Ann. Statist., submitted, 2004.

[12] S. Smale and D.-X. Zhou. Estimating the approximation error in learning theory. Anal. Appl., 1:17–41, 2003.

[13] I. Steinwart. Sparseness of support vector machines. J. Mach. Learn. Res., 4:1071– 1105, 2003.