Kernel-based interpolation at approximate Fekete points

by   Toni Karvonen, et al.

We construct approximate Fekete point sets for kernel-based interpolation by maximising the determinant of a kernel Gram matrix obtained via truncation of an orthonormal expansion of the kernel. Uniform error estimates are proved for kernel interpolants at the resulting points. If the kernel is Gaussian we show that the approximate Fekete points in one dimension are the solution to a convex optimisation problem and that the interpolants convergence with a super-exponential rate. A numerical experiment is provided for the Gaussian kernel.


page 1

page 2

page 3

page 4


Product Kernel Interpolation for Scalable Gaussian Processes

Recent work shows that inference for Gaussian processes can be performed...

Stability of convergence rates: Kernel interpolation on non-Lipschitz domains

Error estimates for kernel interpolation in Reproducing Kernel Hilbert S...

Super-Samples from Kernel Herding

We extend the herding algorithm to continuous spaces by using the kernel...

On iterated interpolation

Matrices resulting from the discretization of a kernel function, e.g., i...

A Geometric Approach for Computing the Kernel of a Polyhedron

We present a geometric algorithm to compute the geometric kernel of a ge...

Kernel interpolation with continuous volume sampling

A fundamental task in kernel methods is to pick nodes and weights, so as...

Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity

We present and study approximate notions of dimensional and margin compl...