On dimension-independent rates of convergence for function approximation with Gaussian kernels
From MaRDI portal
algorithmconvergenceerror boundsGaussian kernelKriging methodlinear functionalreproducing kernel Hilbert spacesshape parametertractabilityworst case
Rate of convergence, degree of approximation (41A25) Multidimensional problems (41A63) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Algorithms for approximation of functions (65D15) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)
Abstract: This article studies the problem of approximating functions belonging to a Hilbert space with an isotropic or anisotropic Gaussian reproducing kernel, K_d(�x,�t) = expleft(-sum_{ell=1}^dgamma_ell^2(x_ell-t_ell)^2
ight) mbox{for all} �x,�tin
eals^d. The isotropic case corresponds to using the same shape parameters for all coordinates, namely for all , whereas the anisotropic case corresponds to varying shape parameters . We are especially interested in moderate to large .
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
Cited in
(36)- Multivariate approximation for analytic functions with Gaussian kernels
- Average case tractability of multivariate approximation with Gaussian kernels
- Kernel-based interpolation at approximate Fekete points
- Convergence of sparse grid Gaussian convolution approximation for multi-dimensional periodic functions
- Asymptotic analysis in multivariate average case approximation with Gaussian kernels
- Countable tensor products of Hermite spaces and spaces of Gaussian kernels
- Inverse multi-quadric RBF for computing the weights of FD method: application to American options
- Cover-based bounds on the numerical rank of Gaussian kernels
- An introduction to the Hilbert-Schmidt SVD using iterated Brownian bridge kernels
- Summation of Gaussian shifts as Jacobi's third theta function
- Exponential tractability of \(L_2\)-approximation with function values
- A simplified criterion for quasi-polynomial tractability of approximation of random elements and its applications
- Optimal designs of positive definite kernels for scattered data approximation
- A kernel-based collocation method for elliptic partial differential equations with random coefficients
- Multivariate integration for analytic functions with Gaussian kernels
- Tractability of function approximation with product kernels
- scientific article; zbMATH DE number 5008057 (Why is no real title available?)
- Gauss-Hermite quadratures for functions from Hilbert spaces with Gaussian reproducing kernels
- Application of the nonuniform fast Fourier transform to the direct numerical simulation of two-way coupled particle laden flows
- Integration in reproducing kernel Hilbert spaces of Gaussian kernels
- Stable Interpolation with Isotropic and Anisotropic Gaussians Using Hermite Generating Function
- Average case approximation: convergence and tractability of Gaussian kernels
- Factorization, Symmetrization, and Truncated Transformation of Radial Basis Function-GA Stabilized Gaussian Radial Basis Functions
- Generalized Mercer kernels and reproducing kernel Banach spaces
- Hyperbolic cross approximation in infinite dimensions
- Asymptotic analysis in multivariate worst case approximation with Gaussian kernels
- Uniform approximation of common Gaussian process kernels using equispaced Fourier grids
- Error bounds and the asymptotic setting in kernel-based approximation
- Orthonormal expansions for translation-invariant kernels
- Moduli of smoothness, \(K\)-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
- Product kernels are efficient and flexible tools for high-dimensional scattered data interpolation
- Infinite-variate L^2-approximation with nested subspace sampling
- Adaptive meshfree approximation for linear elliptic partial differential equations with PDE-greedy kernel methods
- Lengthscale-informed sparse grids for kernel methods in high dimensions
- Approximation of functions: optimal sampling and complexity
- Approximation in Hilbert spaces of the Gaussian and related analytic 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)
