Gaussian Distributions on Riemannian Symmetric Spaces: Statistical Learning With Structured Covariance Matrices

DOI10.1109/TIT.2017.2713829zbMATH Open1464.62300arXiv1607.06929OpenAlexW2963856272WikidataQ115263236 ScholiaQ115263236MaRDI QIDQ4566664FDOQ4566664

Authors: Salem Said, Hatem Hajri, Lionel Bombrun, Baba C. Vemuri 

Publication date: 27 June 2018

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: The Riemannian geometry of covariance matrices has been essential to several successful applications, in computer vision, biomedical signal and image processing, and radar data processing. For these applications, an important ongoing challenge is to develop Riemannian-geometric tools which are adapted to structured covariance matrices. The present paper proposes to meet this challenge by introducing a new class of probability distributions, Gaussian distributions of structured covariance matrices. These are Riemannian analogs of Gaussian distributions, which only sample from covariance matrices having a preassigned structure, such as complex, Toeplitz, or block-Toeplitz. The usefulness of these distributions stems from three features: (1) they are completely tractable, analytically or numerically, when dealing with large covariance matrices, (2) they provide a statistical foundation to the concept of structured Riemannian barycentre (i.e. Fr'echet or geometric mean), (3) they lead to efficient statistical learning algorithms, which realise, among others, density estimation and classification of structured covariance matrices. The paper starts from the observation that several spaces of structured covariance matrices, considered from a geometric point of view, are Riemannian symmetric spaces. Accordingly, it develops an original theory of Gaussian distributions on Riemannian symmetric spaces, of their statistical inference, and of their relationship to the concept of Riemannian barycentre. Then, it uses this original theory to give a detailed description of Gaussian distributions of three kinds of structured covariance matrices, complex, Toeplitz, and block-Toeplitz. Finally, it describes algorithms for density estimation and classification of structured covariance matrices, based on Gaussian distribution mixture models.

Full work available at URL: https://arxiv.org/abs/1607.06929

Recommendations

• Riemannian Gaussian Distributions on the Space of Symmetric Positive Definite Matrices
• Multivariate normal distributions parametrized as a Riemannian symmetric space
• Learning and approximation by Gaussians on Riemannian manifolds
• Gaussian distributions on Riemannian symmetric spaces of nonpositive curvature
• Riemannian Structures on Shape Spaces: A Framework for Statistical Inferences
• Riemannian distances between covariance operators and Gaussian processes
• Riemannian Gaussian distributions, random matrix ensembles and diffusion kernels
• Regression models on Riemannian symmetric spaces
• Geometric structures arising from kernel density estimation on Riemannian manifolds

Mathematics Subject Classification ID

Density estimation (62G07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Estimation in multivariate analysis (62H12) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Stochastic matrices (15B51)

Cited In (15)

• Differential geometry with extreme eigenvalues in the positive semidefinite cone
• Warped Riemannian metrics for location-scale models
• A hyperbolic approach for learning communities on graphs
• A universal, canonical dispersive ordering in metric spaces
• Statistics on the Stiefel manifold: theory and applications
• From Bayesian inference to MCMC and convex optimisation in Hadamard manifolds
• Gaussian distributions on Riemannian symmetric spaces in the large \(N\) limit
• Riemannian Gaussian distributions, random matrix ensembles and diffusion kernels
• Wrapped Statistical Models on Manifolds: Motivations, The Case SE(n), and Generalization to Symmetric Spaces
• A Practical Hands-on for Learning Graph Data Communities on Manifolds
• Global and local scaling limits for the \(\beta=2\) Stieltjes-Wigert random matrix ensemble
• Riemannian barycentres of Gibbs distributions: new results on concentration and convexity in compact symmetric spaces
• Exponential-Wrapped Distributions on Symmetric Spaces
• Introduction to Riemannian Geometry and Geometric Statistics: From Basic Theory to Implementation with Geomstats
• A nonlocal denoising algorithm for manifold-valued images using second order statistics

This page was built for publication: Gaussian Distributions on Riemannian Symmetric Spaces: Statistical Learning With Structured Covariance Matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4566664)