On dimension-independent rates of convergence for function approximation with Gaussian kernels

DOI10.1137/10080138XzbMATH Open1243.65025arXiv1012.2605OpenAlexW2049196399MaRDI QIDQ2882341FDOQ2882341

Authors: Gregory E. Fasshauer, Fred J. Hickernell, H. Woźniakowski 

Publication date: 4 May 2012

Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)

Abstract: This article studies the problem of approximating functions belonging to a Hilbert space $H_d$ with an isotropic or anisotropic Gaussian reproducing kernel, ${\displaystyle }$ K_d(�x,�t) = expleft(-sum_{ell=1}^dgamma_ell^2(x_ell-t_ell)^2 ight) mbox{for all} �x,�tin eals^d. ${\displaystyle }$ The isotropic case corresponds to using the same shape parameters for all coordinates, namely $gamm{a}_{e}ll=gamma>0$ for all $ell$, whereas the anisotropic case corresponds to varying shape parameters $gamm{a}_{e}ll$. We are especially interested in moderate to large $d$.

Full work available at URL: https://arxiv.org/abs/1012.2605

Recommendations

• Multivariate approximation for analytic functions with Gaussian kernels
• Average case approximation: convergence and tractability of Gaussian kernels
• Integration in reproducing kernel Hilbert spaces of Gaussian kernels
• Average case tractability of multivariate approximation with Gaussian kernels
• Tractability of function approximation with product kernels

zbMATH Keywords

convergenceerror boundsreproducing kernel Hilbert spacesalgorithmlinear functionalshape parametertractabilityGaussian kernelKriging methodworst case

Mathematics Subject Classification ID

Multidimensional problems (41A63) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Algorithms for approximation of functions (65D15) Rate of convergence, degree of approximation (41A25)

Cited In (30)

• Error bounds and the asymptotic setting in kernel-based approximation
• Convergence of sparse grid Gaussian convolution approximation for multi-dimensional periodic functions
• Generalized Mercer kernels and reproducing kernel Banach spaces
• Asymptotic analysis in multivariate average case approximation with Gaussian kernels
• A simplified criterion for quasi-polynomial tractability of approximation of random elements and its applications
• Title not available (Why is that?)
• Optimal designs of positive definite kernels for scattered data approximation
• Orthonormal expansions for translation-invariant kernels
• Tractability of function approximation with product kernels
• Moduli of smoothness, \(K\)-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
• Gauss-Hermite quadratures for functions from Hilbert spaces with Gaussian reproducing kernels
• Integration in reproducing kernel Hilbert spaces of Gaussian kernels
• Hyperbolic cross approximation in infinite dimensions
• Countable tensor products of Hermite spaces and spaces of Gaussian kernels
• Multivariate integration for analytic functions with Gaussian kernels
• Inverse multi-quadric RBF for computing the weights of FD method: application to American options
• Kernel-based interpolation at approximate Fekete points
• Uniform approximation of common Gaussian process kernels using equispaced Fourier grids
• Multivariate approximation for analytic functions with Gaussian kernels
• Factorization, Symmetrization, and Truncated Transformation of Radial Basis Function-GA Stabilized Gaussian Radial Basis Functions
• A kernel-based collocation method for elliptic partial differential equations with random coefficients
• Application of the nonuniform fast Fourier transform to the direct numerical simulation of two-way coupled particle laden flows
• Asymptotic analysis in multivariate worst case approximation with Gaussian kernels
• Summation of Gaussian shifts as Jacobi's third theta function
• Stable Interpolation with Isotropic and Anisotropic Gaussians Using Hermite Generating Function
• An introduction to the Hilbert-Schmidt SVD using iterated Brownian bridge kernels
• Cover-based bounds on the numerical rank of Gaussian kernels
• Exponential tractability of \(L_2\)-approximation with function values
• Average case approximation: convergence and tractability of Gaussian kernels
• Average case tractability of multivariate approximation with Gaussian kernels

This page was built for publication: On dimension-independent rates of convergence for function approximation with Gaussian kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2882341)