Power series kernels
Interpolation in approximation theory (41A05) Approximation by polynomials (41A10) Rate of convergence, degree of approximation (41A25) Series expansions (e.g., Taylor, Lidstone series, but not Fourier series) (41A58) Multidimensional problems (41A63) Learning and adaptive systems in artificial intelligence (68T05)
Let \(\alpha\in\mathbb{N}_{0}^{d}\) and let \(w_{\alpha}\) be a positive real number such that \(\sum_{\alpha\in\mathbb{N}_{0}^{d}}\) \(\frac{w_{\alpha}}{(\alpha!)^{2}}\) \(<\infty\) holds. The expression \(K(x,y)=\sum_{\alpha\in\mathbb{N}_{0}^{d} }w_{\alpha}\frac{x^{\alpha}y^{a}}{(\alpha!)^{2}}\) where \(x,y\in\Omega \subset\mathbb{R}^{d}\) is called a power series kernel (PSK for short). The author considers the PSK and under weak additional conditions on the weights \(w_{\alpha},\) she determines the ``native Hilbert space \(\mathcal{N}_{K}\) of multivariate functions in which the kernels \(K(x,y)\) are reproducing. For a function \(f\in\mathcal{N}_{K}\) and \(X=\{x_{1},x_{2},\dots ,x_{N}\}\subset\Omega\) the author considers the uniquely determined interpolant of the form \(s_{f,X}(x)=\sum_{j=1}^{N}\alpha_{j}K(x,x_{j})\) satisfying \(s_{f,X} (x_{k})=f(x_{k})\) for \(k=1,2,\dots ,N\) and the error between \(f\) and its interpolant \(s_{f,X}\) are expressed in terms of the fill distance \(h:=h_{X,\Omega}:=\sup_{x\in\Omega}\min_{x_{j}\in X}\| x-x_{j} \|_{2}\). She shows that the convergence occurs for the function and all derivatives, when \(h\rightarrow0\). Finally, by truncation of the interpolant one obtains a multivariate polynomial \(T^{(k)}s_{f,X}\) and the approximation error between \(f\) and \(T^{(k)}s_{f,X}\) is studied. So the classical Bernstein theorem concerning polynomial approximation of analytic functions is extended to the multivariate case. An application to machine learning algorithm is presented.
- Approximate interpolation with applications to selecting smoothing parameters
- Approximation polynomiale de fonctions \(C^ \infty\) et analytiques
- Bounds on multivariate polynomials and exponential error estimates for multiquadric interpolation
- scientific article; zbMATH DE number 823069 (Why is no real title available?)
- scientific article; zbMATH DE number 3285437 (Why is no real title available?)
- Interpolation in the limit of increasingly flat radial basis functions
- Inverse and saturation theorems for radial basis function interpolation
- Learning with generalization capability by kernel methods of bounded complexity
- Multivariate interpolation by polynomials and radial basis functions
- On multivariate polynomial interpolation
- Positive definite dot product kernels in learning theory
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Scattered Data Approximation
- Worst-case optimal approximation with increasingly flat Gaussian kernels
- Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere
- An introduction to the Hilbert-Schmidt SVD using iterated Brownian bridge kernels
- Generalized Whittle-Matérn and polyharmonic kernels
- Small sample spaces for Gaussian processes
- Decay of singular values of power series kernels on the sphere
- Interpolation and approximation in Taylor spaces
- On the numerical rank of radial basis function kernels in high dimensions
- scientific article; zbMATH DE number 810380 (Why is no real title available?)
- Improved exponential convergence rates by oversampling near the boundary
- On the inclusion relation of reproducing kernel Hilbert spaces
- Sampling and Stability
- Variable selection for nonparametric learning with power series kernels
- Generalized support vector regression: duality and tensor-kernel representation
- On the reduction of global error of multivariate higher-order product polynomial kernels
- Multiscale approximation and reproducing kernel Hilbert space methods
- Reproducing kernel Hilbert spaces for parametric partial differential equations
- Generalized Mercer kernels and reproducing kernel Banach spaces
- Kernel Approximation on Algebraic Varieties
- Nuclearity for power series kernels in higher dimensions
- Construction of Multivariate Polynomial Approximation Kernels via Semidefinite Programming
- Interpolation with the polynomial kernels
- Orthonormal expansions for translation-invariant kernels
- Optimal compactly supported functions in Sobolev spaces
- Approximation in Hilbert spaces of the Gaussian and related analytic kernels
- Sampling inequalities for infinitely smooth functions, with applications to interpolation and machine learning
This page was built for publication: Power series kernels
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q734058)
