Advertisement

Mercer’s Theorem, Feature Maps, and Smoothing

  • Ha Quang Minh
  • Partha Niyogi
  • Yuan Yao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4005)

Abstract

We study Mercer’s theorem and feature maps for several positive definite kernels that are widely used in practice. The smoothing properties of these kernels will also be explored.

Keywords

Orthonormal Basis Spherical Harmonic Gaussian Kernel Reproduce Kernel Hilbert Space Polynomial Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aronszajn, N.: Theory of Reproducing Kernels. Transactions of the American Mathematical Society 68, 337–404 (1950)CrossRefMathSciNetMATHGoogle Scholar
  2. 2.
    Belkin, M., Niyogi, P., Sindwani, V.: Manifold Regularization: a Geometric Framework for Learning from Examples. University of Chicago Computer Science Technical Report TR-2004-06 (2004) (accepted for publication)Google Scholar
  3. 3.
    Belkin, M., Niyogi, P.: Semi-supervised Learning on Riemannian Manifolds. Machine Learning, Special Issue on Clustering 56, 209–239 (2004)MATHGoogle Scholar
  4. 4.
    De Vito, E., Caponnetto, A., Rosasco, L.: Model Selection for Regularized Least-Squares Algorithm in Learning Theory. Foundations of Computational Mathematics 5(1), 59–85 (2005)CrossRefMathSciNetMATHGoogle Scholar
  5. 5.
    Lafferty, J., Lebanon, G.: Diffusion Kernels on Statistical Manifolds. Journal of Machine Learning Research 6, 129–163 (2005)MathSciNetGoogle Scholar
  6. 6.
    Müller, C.: Analysis of Spherical Symmetries in Euclidean Spaces. In: Applied Mathematical Sciences 129. Springer, New York (1997)Google Scholar
  7. 7.
    Schölkopf, B., Smola, A.J.: Learning with Kernels. The MIT Press, Cambridge, Massachusetts (2002)Google Scholar
  8. 8.
    Smale, S., Zhou, D.X.: Learning Theory Estimates via Integral Operators and Their Approximations (to appear, 2005)Google Scholar
  9. 9.
    Smola, A.J., Ovari, Z.L., Williamson, R.C.: Regularization with Dot-Product Kernels. In: Advances in Information Processing Systems (2000)Google Scholar
  10. 10.
    Steinwart, I., Hush, D., Scovel, C.: An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels Kernels. Los Alamos National Laboratory Technical Report LA-UR-04-8274 (December 2005)Google Scholar
  11. 11.
    Wahba, G.: Spline Interpolation and Smoothing on the Sphere. SIAM Journal of Scientific and Statistical Computing 2, 5–16 (1981)CrossRefMathSciNetMATHGoogle Scholar
  12. 12.
    Wahba, G.: Spline Models for Observational Data. CBMS-NSF Regional Conference Series in Applied Mathematics 59, Society for Industrial and Applied Mathematics, Philadelphia (1990)Google Scholar
  13. 13.
    Watson, G.N.: A Treatise on the Theory of Bessel Functions, 2nd edn. Cambridge University Press, Cambridge, England (1944)MATHGoogle Scholar
  14. 14.
    Zhou, D.X.: The Covering Number in Learning Theory. Journal of Complexity 18, 739–767 (2002)CrossRefMathSciNetMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ha Quang Minh
    • 1
  • Partha Niyogi
    • 1
  • Yuan Yao
    • 2
  1. 1.Department of Computer ScienceUniversity of ChicagoChicagoUSA
  2. 2.Department of MathematicsUniversity of California, BerkeleyBerkeleyUSA

Personalised recommendations