Gaussian kernels on non-simply-connected closed Riemannian manifolds are never positive definite

03/12/2023
by   Siran Li, et al.
0

We show that the Gaussian kernel exp{-λ d_g^2(∙, ∙)} on any non-simply-connected closed Riemannian manifold (ℳ,g), where d_g is the geodesic distance, is not positive definite for any λ > 0, combining analyses in the recent preprint [9] by Da Costa–Mostajeran–Ortega and classical comparison theorems in Riemannian geometry.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/30/2014

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels

In this paper, we develop an approach to exploiting kernel methods with ...
research
11/02/2014

Geodesic Exponential Kernels: When Curvature and Linearity Conflict

We consider kernel methods on general geodesic metric spaces and provide...
research
01/19/2023

Strictly positive definite kernels on compact Riemannian manifolds

The paper studies strictly positive definite kernels on compact Riemanni...
research
12/13/2014

Optimizing Over Radial Kernels on Compact Manifolds

We tackle the problem of optimizing over all possible positive definite ...
research
07/28/2020

Symmetric Positive Semi-definite Riemannian Geometry with Application to Domain Adaptation

In this paper, we present new results on the Riemannian geometry of symm...
research
05/03/2023

Low-complexity subspace-descent over symmetric positive definite manifold

This work puts forth low-complexity Riemannian subspace descent algorith...
research
02/04/2016

Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions

We present a comparative evaluation of various techniques for action rec...

Please sign up or login with your details

Forgot password? Click here to reset