Fisher-Rao distance on the covariance cone

10/29/2020

∙

The Fisher-Rao geodesic distance on the statistical manifold consisting of zero-mean p-dimensional multivariate Gaussians appears without proof in several places (such as Steven Smith's "Covariance, Subspace, and Intrinsic Cramer-Rao Bounds"). In this paper, we give a proof using basic Riemannian geometry.

READ FULL TEXT

Fisher-Rao distance on the covariance cone

The Fisher Geometry and Geodesics of the Multivariate Normals, without Differential Geometry

Bures-Wasserstein Geometry

Connecting Dots -- from Local Covariance to Empirical Intrinsic Geometry and Locally Linear Embedding

Regularization of covariance matrices on Riemannian manifolds using linear systems

A Basic Treatment of the Distance Covariance

Fisher-Rao distance and pullback SPD cone distances between multivariate normal distributions

Intrinsic Analysis of the Sample Fréchet Mean and Sample Mean of Complex Wishart Matrices

Fisher-Rao distance on the covariance cone

Related Research

The Fisher Geometry and Geodesics of the Multivariate Normals, without Differential Geometry

Bures-Wasserstein Geometry

Connecting Dots -- from Local Covariance to Empirical Intrinsic Geometry and Locally Linear Embedding

Regularization of covariance matrices on Riemannian manifolds using linear systems

A Basic Treatment of the Distance Covariance

Fisher-Rao distance and pullback SPD cone distances between multivariate normal distributions

Intrinsic Analysis of the Sample Fréchet Mean and Sample Mean of Complex Wishart Matrices