Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry

DOI10.1007/978-3-031-38271-0_40arXiv2110.10464OpenAlexW4385435062MaRDI QIDQ6138145

Pratik Jawanpuria, Junbin Gao, Unnamed Author, Bamdev Mishra

Publication date: 16 January 2024

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.10464

zbMATH Keywords

symmetric positive definite matricesBures-Wasserstein geometry

Mathematics Subject Classification ID

Differential geometric aspects of statistical manifolds and information geometry (53B12)

Cites Work

• Unnamed Item
• Unnamed Item
• Computational Optimal Transport: With Applications to Data Science
• Sparse inverse covariance estimation with the graphical lasso
• Wasserstein Riemannian geometry of Gaussian densities
• Bures-Wasserstein geometry for positive-definite Hermitian matrices and their trace-one subset
• Riemannian optimization with a preconditioning scheme on the generalized Stiefel manifold
• An alternative to EM for Gaussian mixture models: batch and stochastic Riemannian optimization
• Curvature of the manifold of fixed-rank positive-semidefinite matrices endowed with the Bures-Wasserstein metric
• On the Bures-Wasserstein distance between positive definite matrices
• A Riemannian framework for tensor computing
• Riemannian Preconditioning
• Positive definite matrices and the S-divergence
• Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation
• Manopt, a Matlab toolbox for optimization on manifolds
• Positive Definite Matrices
• ROPTLIB
• An Introduction to Optimization on Smooth Manifolds
• Riemannian Geometry of Symmetric Positive Definite Matrices via Cholesky Decomposition
• Stochastic Gradient Descent on Riemannian Manifolds

This page was built for publication: Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry