Multivariate Generalized Gaussian Distribution: Convexity and Graphical Models

DOI10.1109/TSP.2013.2267740MaRDI QIDQ4578694zbMATH OpenDBLPWikidataFDO

Authors Teng Zhang, Ami Wiesel, M. Greco

Publication date 22 August 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1304.3206

Mathematics Subject Classification ID

Graphical methods in statistics (62A09) Estimation in multivariate analysis (62H12) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: We consider covariance estimation in the multivariate generalized Gaussian distribution (MGGD) and elliptically symmetric (ES) distribution. The maximum likelihood optimization associated with this problem is non-convex, yet it has been proved that its global solution can be often computed via simple fixed point iterations. Our first contribution is a new analysis of this likelihood based on geodesic convexity that requires weaker assumptions. Our second contribution is a generalized framework for structured covariance estimation under sparsity constraints. We show that the optimizations can be formulated as convex minimization as long the MGGD shape parameter is larger than half and the sparsity pattern is chordal. These include, for example, maximum likelihood estimation of banded inverse covariances in multivariate Laplace distributions, which are associated with time varying autoregressive processes.

Cited in

(12)

• Mixtures of multivariate power exponential distributions
• Inference and mixture modeling with the elliptical Gamma distribution
• Linear and graphical models for the multivariate complex normal distribution
• Distributed parameter estimation for univariate generalized Gaussian distribution over sensor networks
• Shrinking the Covariance Matrix Using Convex Penalties on the Matrix-Log Transformation
• Conic geometric optimization on the manifold of positive definite matrices
• Novel Simple Representations for Gaussian Class Multivariate Distributions With Generalized Correlation
• On strong identifiability and convergence rates of parameter estimation in finite mixtures
• Riemannian optimization via Frank-Wolfe methods
• Sparse precision matrix estimation under lower polynomial moment assumption
• The sparseness of g-convex functions
• An extensible framework for the probabilistic search of stochastically-moving targets characterized by generalized Gaussian distributions or experimentally-defined regions of interest

This page was built for publication: Multivariate Generalized Gaussian Distribution: Convexity and Graphical Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4578694)