• Corpus ID: 239049655

Generalized Bures-Wasserstein Geometry for Positive Definite Matrices

@inproceedings{Han2021GeneralizedBG,
title={Generalized Bures-Wasserstein Geometry for Positive Definite Matrices},
author={Andi Han and Bamdev Mishra and Pratik Jawanpuria and Junbin Gao},
year={2021}
}
• Andi Han, +1 author Junbin Gao
• Published 20 October 2021
• Mathematics
This paper proposes a generalized Bures-Wasserstein (BW) Riemannian geometry for the manifold of symmetric positive definite matrices. We explore the generalization of the BW geometry in three different ways: 1) by generalizing the Lyapunov operator in the metric, 2) by generalizing the orthogonal Procrustes distance, and 3) by generalizing the Wasserstein distance between the Gaussians. We show that they all lead to the same geometry. The proposed generalization is parameterized by a symmetric…
1 Citations

Figures and Tables from this paper

On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
• Computer Science, Mathematics
ArXiv
• 2021
This study comparatively analyzes the Bures-Wasserstein geometry with the popular Affine-Invariant geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold to show that the BW metric is a more suitable and robust choice for several RiemANNian optimization problems over ill-conditioned SPD matrices.

References

SHOWING 1-10 OF 56 REFERENCES
On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
• Computer Science, Mathematics
ArXiv
• 2021
This study comparatively analyzes the Bures-Wasserstein geometry with the popular Affine-Invariant geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold to show that the BW metric is a more suitable and robust choice for several RiemANNian optimization problems over ill-conditioned SPD matrices.
Wasserstein Riemannian geometry of Gaussian densities
• Mathematics
Information Geometry
• 2018
The Wasserstein distance on multivariate non-degenerate Gaussian densities is a Riemannian distance. After reviewing the properties of the distance and the metric geodesic, we present an explicit
On the Bures–Wasserstein distance between positive definite matrices
• Mathematics
Expositiones Mathematicae
• 2019
The metric $d(A,B)=\left[ \tr\, A+\tr\, B-2\tr(A^{1/2}BA^{1/2})^{1/2}\right]^{1/2}$ on the manifold of $n\times n$ positive definite matrices arises in various optimisation problems, in quantum
A Unified Formulation for the Bures-Wasserstein and Log-Euclidean/Log-Hilbert-Schmidt Distances between Positive Definite Operators
• H. Minh
• Computer Science, Mathematics
GSI
• 2019
This work presents a parametrized family of distances, namely the Alpha Procrustes distances, on the set of symmetric, positive definite (SPD) matrices, which provide a unified formulation encompassing both the Bures-Wasserstein and Log-Euclidean distances between SPD matrices.
Curvature of the Manifold of Fixed-Rank Positive-Semidefinite Matrices Endowed with the Bures-Wasserstein Metric
• Computer Science, Mathematics
GSI
• 2019
This work considers the manifold of rank-p positive-semidefinite matrices of size n as a quotient of the set of full-rank n-by-p matrices by the orthogonal group in dimension p, and obtains expressions for the Riemannian curvature tensor and the sectional curvature of the manifold.
Positive definite matrices and the S-divergence
Positive definite matrices abound in a dazzling variety of applications. This ubiquity can be in part attributed to their rich geometric structure: positive definite matrices form a self-dual convex
Conic Geometric Optimization on the Manifold of Positive Definite Matrices
• Mathematics, Computer Science
SIAM J. Optim.
• 2015
This work develops theoretical tools to recognize and generate g-convex functions as well as cone theoretic fixed-point optimization algorithms and illustrates their techniques by applying them to maximum-likelihood parameter estimation for elliptically contoured distributions.
A Riemannian Framework for Tensor Computing
• Mathematics, Computer Science
International Journal of Computer Vision
• 2005
This paper proposes to endow the tensor space with an affine-invariant Riemannian metric and demonstrates that it leads to strong theoretical properties: the cone of positive definite symmetric matrices is replaced by a regular and complete manifold without boundaries, the geodesic between two tensors and the mean of a set of tensors are uniquely defined.
Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds
• Mathematics, Computer Science
NIPS
• 2017
The global convergence properties of the accelerated first-order method for geodesically convex optimization, which is the generalization of the standard Nesterov's accelerated method from Euclidean space to nonlinear Riemannian space, are analyzed.
A new metric on the manifold of kernel matrices with application to matrix geometric means
• S. Sra
• Mathematics, Computer Science
NIPS
• 2012
A new metric on spd matrices is introduced, which not only respects non-Euclidean geometry but also offers faster computation than δR while being less complicated to use.