On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

Abstract

In this paper, we comparatively analyze the Bures-Wasserstein (BW) geometry with the popular Affine-Invariant (AI) geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold. Our study begins with an observation that the BW metric has a linear dependence on SPD matrices in contrast to the quadratic dependence of the AI metric. We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-conditioned SPD matrices. We show that the BW geometry has a non-negative curvature, which further improves convergence rates of algorithms over the non-positively curved AI geometry. Finally, we verify that several popular cost functions, which are known to be geodesic convex under the AI geometry, are also geodesic convex under the BW geometry. Extensive experiments on various applications support our findings.

References in corpus (16)

• Manopt, a Matlab toolbox for optimization on manifolds
• Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
• Low-rank optimization for semidefinite convex problems
• Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach
• Conic geometric optimisation on the manifold of positive definite matrices
• A Riemannian Network for SPD Matrix Learning
• Riemannian Geometry of Symmetric Positive Definite Matrices via Cholesky Decomposition
• Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport
• Regression on fixed-rank positive semidefinite matrices: a Riemannian approach
• Geodesic Convex Optimization: Differentiation on Manifolds, Geodesics, and Convexity
• McTorch, a manifold optimization library for deep learning
• Kernel Wasserstein Distance
• On Wasserstein geometry of the space of Gaussian measures
• MixEst: An Estimation Toolbox for Mixture Models
• Is affine invariance well defined on SPD matrices? A principled continuum of metrics
• Variance reduction for Riemannian non-convex optimization with batch size adaptation

Cited by in corpus (2)

• Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry
• Riemannian-geometric generalizations of quantum fidelities and Bures-Wasserstein distance