Sobolev Spaces, Kernels and Discrepancies over Hyperspheres

11/16/2022
by   Simon Hubbert, et al.
0

This work provides theoretical foundations for kernel methods in the hyperspherical context. Specifically, we characterise the native spaces (reproducing kernel Hilbert spaces) and the Sobolev spaces associated with kernels defined over hyperspheres. Our results have direct consequences for kernel cubature, determining the rate of convergence of the worst case error, and expanding the applicability of cubature algorithms based on Stein's method. We first introduce a suitable characterisation on Sobolev spaces on the d-dimensional hypersphere embedded in (d+1)-dimensional Euclidean spaces. Our characterisation is based on the Fourier–Schoenberg sequences associated with a given kernel. Such sequences are hard (if not impossible) to compute analytically on d-dimensional spheres, but often feasible over Hilbert spheres. We circumvent this problem by finding a projection operator that allows to Fourier mapping from Hilbert into finite dimensional hyperspheres. We illustrate our findings through some parametric families of kernels.

READ FULL TEXT
research
05/27/2019

Reproducing kernel Hilbert spaces on manifolds: Sobolev and Diffusion spaces

We study reproducing kernel Hilbert spaces (RKHS) on a Riemannian mani...
research
09/26/2022

Approximation in Hilbert spaces of the Gaussian and other weighted power series kernels

This article considers linear approximation based on function evaluation...
research
01/30/2020

Reproducing kernels based schemes for nonparametric regression

In this work, we develop and study an empirical projection operator sche...
research
09/28/2022

Minimax Optimal Kernel Operator Learning via Multilevel Training

Learning mappings between infinite-dimensional function spaces has achie...
research
02/27/2019

TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces

The proposed work aims at proposing a alternative kernel decomposition i...
research
04/26/2023

Kernel Methods are Competitive for Operator Learning

We present a general kernel-based framework for learning operators betwe...
research
07/11/2012

Exponential Families for Conditional Random Fields

In this paper we de ne conditional random elds in reproducing kernel Hil...

Please sign up or login with your details

Forgot password? Click here to reset