论文信息 - Mercer theorem for RKHS on noncompact sets

Mercer theorem for RKHS on noncompact sets

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.

Hongwei Sun | Hongwei Sun

[1] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[3] Federico Girosi,et al. An Equivalence Between Sparse Approximation and Support Vector Machines , 1998, Neural Computation.

[4] G. Wahba. Spline models for observational data , 1990 .

[5] Felipe Cucker,et al. On the mathematical foundations of learning , 2001 .

[6] Ding-Xuan Zhou,et al. Capacity of reproducing kernel spaces in learning theory , 2003, IEEE Transactions on Information Theory.

[7] Tomaso A. Poggio,et al. Regularization Networks and Support Vector Machines , 2000, Adv. Comput. Math..

[8] Ding-Xuan Zhou,et al. The covering number in learning theory , 2002, J. Complex..

[9] S. Smale,et al. ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY , 2003 .

[10] N. Aronszajn. Theory of Reproducing Kernels. , 1950 .

[11] Felipe Cucker,et al. Best Choices for Regularization Parameters in Learning Theory: On the Bias—Variance Problem , 2002, Found. Comput. Math..

[12] J. Mercer. Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .