paper

Tractability of the function approximation problem in terms of the kernel's shape and scale parameters

arXiv:1411.0790

Abstract

This article studies the problem of approximating functions belonging to a Hilbert space with a reproducing kernel of the form $$\tilde K_d(\boldsymbol x,\boldsymbol t):=\prod_{\ell=1}^d \left(1-α_\ell^2+α_\ell^2K_{γ_\ell}(x_\ell,t_\ell)\right)\ \ \ \mbox{for all} \ \ \ \boldsymbol x,\boldsymbol t\in\mathbb R^d.$$ The are scale parameters, and the are sometimes called shape parameters. The reproducing kernel corresponds to some Hilbert space of functions defined on . The kernel generalizes the anisotropic Gaussian reproducing kernel, whose tractability properties have been established in the literature. We present sufficient conditions on under which polynomial tractability holds for function approximation problems on . The exponent of strong polynomial tractability arises from bounds on the eigenvalues of a positive definite linear operator.

15 pages. arXiv admin note: text overlap with arXiv:1012.2605

References in corpus (1)