Abstract
In this chapter we summarize density properties of Reproducing Kernel Hilbert Spaces induced by different classes of kernels. They are important to characterize the power of the associated hypothesis spaces. In the process we characterize the role of b, which is the constant in the standard form of the solution provided by the Support Vector Machine technique \(f(x) = \sum\nolimits_{i = 1}^\ell {\alpha _i } K\left( {x,\:x_i } \right) + b,\) which is a special case of Regularization Machines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
N. Aronszajn Theory of reproducing kernels Trans. Amer. Math. Soc., vol. 686, pp. 337–404, 1950.
C. Berg, J.P.R. Christensen, and P. Ressel Harmonic Analysis on Semigroups: Theory of Positive Definite and Related Functions Springer, 1984.
R. Courant and D. Hilbert Methods of Mathematical Physics, Vol 2 Interscience, 1962.
F. Cucker and S. Smale On the Mathematical Foundations of Learning, Bull Amer. Math. Soc., vol. 39, pp. 1–49, 2002.
T. Evgeniou, M. Pontil, and T. Poggio Regularization Networks and Support Vector Machines Advances in Computational Mathematics, vol. 13, pp. 1–50, 2000.
T. Friess, N. Cristianini, and C. Campbell The Kernel-Adatron: A fast and simple learning procedure for Support Vector Machines Proceedings of the 15th International Conference in Machine Learning, pages 188–196, 1998.
F. Girosi An equivalence between sparse approximation and support vector machines Neural Computation, vol. 10, pp. 1455–1480, 1998.
F. Girosi and T. Poggio and B. Caprile Extensions of a Theory of Networks for Approximation and Learning: outliers and Negative Examples, Advances in Neural information processings systems 3, R. Lippmann and J. Moody and D. Touretzky, Morgan Kaufmann, 1991, San Mateo, CA.
F. Girosi and T. Poggio Networks and the Best Approximation Property Biological Cybernetics, vol. 63, pp. 169–176, 1990.
F. Girosi, M. Jones, and T. Poggio Regularization theory and neural network architectures Neural Computation, vol. 7, pp. 219–269, 1995.
A.N. Kolmogorov and S.V. Fonim Elements of the Theory of Functions and Functional Analysis Dover, 1957
Y. Lin, Y. Lee, and G. Wahba Support Vector Machines for Classification in Nonstandard Situations TR 1016, March 2000. To appear, Machine Learning
J. Mercer Functions of positive and negative type and their connection with the theory of integral equations Phil.los. Trans. Roy. Soc. London Ser. A, vol. 209, pp. 415–446, 1909.
C.A. Micchelli Interpolation of scattered data: distance matrices and conditionally positive definite functions Constructive Approximation, vol. 2, pp. 11–22, 1986.
T. Poggio, S. Mukherjee, R. Rifkin, A. Rakhlin and A. Verri b CBCL Paper 198/AI Memo 2001-011, Massachusetts Institute of Technology, Cambridge, MA, July 2001
I.J. Schoenberg Metric spaces and completely monotone functions Ann. of Math., vol. 39, pp.811–841, 1938.
A. N. Tikhonov and V. Y. Arsenin Solutions of Ill-posed Problems W. H. Winston, 1977
V.N. Vapnik The Nature of Statistical Learning Theory Springer, 1995.
V.N. Vapnik Statistical Learning Theory Wiley, 1998.
G. Wahba Spline models for observational data SIAM, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Poggio, T., Mukherjee, S., Rifkin, R., Raklin, A., Verri, A. (2002). B. In: Winkler, J., Niranjan, M. (eds) Uncertainty in Geometric Computations. The Springer International Series in Engineering and Computer Science, vol 704. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0813-7_11
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0813-7_11
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5252-5
Online ISBN: 978-1-4615-0813-7
eBook Packages: Springer Book Archive