The Gaussian kernel on the circle and spaces that admit isometric embeddings of the circle

02/21/2023
by   Nathaël Da Costa, et al.
0

On Euclidean spaces, the Gaussian kernel is one of the most widely used kernels in applications. It has also been used on non-Euclidean spaces, where it is known that there may be (and often are) scale parameters for which it is not positive definite. Hope remains that this kernel is positive definite for many choices of parameter. However, we show that the Gaussian kernel is not positive definite on the circle for any choice of parameter. This implies that on metric spaces in which the circle can be isometrically embedded, such as spheres, projective spaces and Grassmannians, the Gaussian kernel is not positive definite for any parameter.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/02/2014

Geodesic Exponential Kernels: When Curvature and Linearity Conflict

We consider kernel methods on general geodesic metric spaces and provide...
research
11/27/2019

Composition operators on reproducing kernel Hilbert spaces with analytic positive definite functions

Composition operators have been extensively studied in complex analysis,...
research
05/10/2022

Dimension Walks on Generalized Spaces

Let d,k be positive integers. We call generalized spaces the cartesian p...
research
09/12/2012

Positivity and Transportation

We prove in this paper that the weighted volume of the set of integral t...
research
09/09/2008

Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning

For supervised and unsupervised learning, positive definite kernels allo...
research
02/24/2020

Handling the Positive-Definite Constraint in the Bayesian Learning Rule

Bayesian learning rule is a recently proposed variational inference meth...
research
09/06/2018

Large Scale Learning with Kreĭn Kernels

We extend the Nyström method for low-rank approximation of positive defi...

Please sign up or login with your details

Forgot password? Click here to reset