An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
Authors:
- I. SteinwartISI. Steinwart
- D. HushDHD. Hush
- C. ScovelCSC. Scovel
- 25 September 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 52 (10) , 4635-4643
Abstract
Although Gaussian radial basis function (RBF) kernels are one of the most often used kernels in modern machine learning methods such as support vector machines (SVMs), little is known about the structure of their reproducing kernel Hilbert spaces (RKHSs). In this work, two distinct explicit descriptions of the RKHSs corresponding to Gaussian RBF kernels are given and some consequences are discussed. Furthermore, an orthonormal basis for these spaces is presented. Finally, it is discussed how the results can be used for analyzing the learning performance of SVMsKeywords
This publication has 13 references indexed in Scilit:
- Fast rates for support vector machines using Gaussian kernelsThe Annals of Statistics, 2007
- Function Classes That Approximate the Bayes RiskLecture Notes in Computer Science, 2006
- Consistency of Support Vector Machines and Other Regularized Kernel ClassifiersIEEE Transactions on Information Theory, 2005
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORYAnalysis and Applications, 2003
- 10.1162/153244302760185252Applied Physics Letters, 2000
- A Probabilistic Theory of Pattern Recognition1996
- Holomorphic Functions and Integral Representations in Several Complex Variables1986
- Introduction to general theory of reproducing kernelsRocky Mountain Journal of Mathematics, 1972
- On a Hilbert space of analytic functions and an associated integral transform part ICommunications on Pure and Applied Mathematics, 1961
- Theory of reproducing kernelsTransactions of the American Mathematical Society, 1950