Mercer theorem for RKHS on noncompact sets. (English) Zbl 1094.46021

Sun, Hongwei

J. Complexity 21, No. 3, 337-349 (2005).

Summary: Reproducing kernel Hilbert spaces are an important family of function spaces and play useful roles in various branches of analysis and applications including the kernel machine learning. When the domain of definition is compact, they can be characterized as the image of the square root of an integral operator, by means of the Mercer theorem. The purpose of this paper is to extend the Mercer theorem to noncompact domains, and to establish a functional analysis characterization of the reproducing kernel Hilbert spaces on general domains.

MSC:

46E22	Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces)
28C15	Set functions and measures on topological spaces (regularity of measures, etc.)
68T05	Learning and adaptive systems in artificial intelligence
68Q32	Computational learning theory

Keywords:

Mercer kernel; Reproducing kernel Hilbert spaces; Nondegenerate Borel measure; Positive semidefiniteness

References:

[1]	Aronszajn, N., Theory of reproducing kernels, Trans. amer. math. soc., 68, 337-404, (1950) · Zbl 0037.20701
[2]	Cucker, F.; Smale, S., On the mathematical foundations of learning, Bull. amer. soc., 39, 1-49, (2001) · Zbl 0983.68162
[3]	Cucker, F.; Smale, S., Best choices for regularization parameters in learning theoryon the bias-variance problem, Found. comput. math., 2, 413-428, (2002) · Zbl 1057.68085
[4]	F. Cucker, D.X. Zhou, Learning Theory, Cambridge University Press, Cambridge.
[5]	Evgeniou, T.; Pontil, M.; Poggio, T., Regularization networks and support vector machines, Adv. comput. math., 13, 1-50, (2000) · Zbl 0939.68098
[6]	Hochstadt, H., Integral equations, (1973), Wiley New York · Zbl 0137.08601
[7]	Mercer, J., Functions of positive and negative type and their connection with the theory of integral equations, Philos. trans. royal soc. London, 209, 415-446, (1909) · JFM 40.0408.02
[8]	Smale, S.; Zhou, D.X., Estimating the approximation error in learning theory, Anal. appl., 1, 17-41, (2003) · Zbl 1079.68089
[9]	Vapnik, V., Statistical learning theory, (1998), Wiley New York · Zbl 0935.62007
[10]	G. Wahba, Spline Models for Observational Data, Series in Applied Mathematics, vol. 59, SIAM, Philadelphia, 1990. · Zbl 0813.62001
[11]	Girosi, F., An equivalence between sparse approximation and support vector machines neural computation, Neural comput., 10, 1455-1480, (1998)
[12]	Zhou, D.X., Capacity of reproducing kernel spaces in learning theory, IEEE trans. inform. theory, 49, 1743-1752, (2003) · Zbl 1290.62033
[13]	Zhou, D.X., The covering number in learning theory, J. complexity, 18, 739-767, (2002) · Zbl 1016.68044