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

2023-03-12 · Siran Li

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

📄 PDF Abstract BibTeX arXiv:2303.06558

Code (0)

등록된 구현이 없습니다.

The Schrödinger Bridge between Gaussian Measures has a Closed Form

2022-02-11 · Charlotte Bunne, Ya-Ping Hsieh, Marco Cuturi, Andreas Krause

The static optimal transport $(\mathrm{OT})$ problem between Gaussians seeks to recover an optimal map, or more generally a coupling, to morph a Gaussian into another. It has been well studied and applied to a wide varie…

Form Gaussian Processes MORPH

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels

2014-11-30 · Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li 외

In this paper, we develop an approach to exploiting kernel methods with manifold-valued data. In many computer vision problems, the data can be naturally represented as points on a Riemannian manifold. Due to the non-Euc…

Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels

2021-10-27 · NeurIPS 2021 12 · Michael Hutchinson, Alexander Terenin, Viacheslav Borovitskiy, So Takao 외

Gaussian processes are machine learning models capable of learning unknown functions in a way that represents uncertainty, thereby facilitating construction of optimal decision-making systems. Motivated by a desire to de…

BIG-bench Machine Learning Decision Making Gaussian Processes Variational Inference

Geodesic Exponential Kernels: When Curvature and Linearity Conflict

2014-11-02 · CVPR 2015 6 · Aasa Feragen, Francois Lauze, Søren Hauberg

We consider kernel methods on general geodesic metric spaces and provide both negative and positive results. First we show that the common Gaussian kernel can only be generalized to a positive definite kernel on a geodes…

Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition With Image Sets

2015-06-01 · CVPR 2015 6 · Wen Wang, Ruiping Wang, Zhiwu Huang, Shiguang Shan 외

This paper presents a method named Discriminant Analysis on Riemannian manifold of Gaussian distributions (DARG) to solve the problem of face recognition with image sets. Our goal is to capture the underlying data distri…

Face Identification Face Recognition Robust classification