Structure estimation for discrete graphical models: Generalized covariance matrices and their inverses

Abstract

We investigate the relationship between the structure of a discrete graphical model and the support of the inverse of a generalized covariance matrix. We show that for certain graph structures, the support of the inverse covariance matrix of indicator variables on the vertices of a graph reflects the conditional independence structure of the graph. Our work extends results that have previously been established only in the context of multivariate Gaussian graphical models, thereby addressing an open question about the significance of the inverse covariance matrix of a non-Gaussian distribution. The proof exploits a combination of ideas from the geometry of exponential families, junction tree theory and convex analysis. These population-level results have various consequences for graph selection methods, both known and novel, including a novel method for structure estimation for missing or corrupted observations. We provide nonasymptotic guarantees for such methods and illustrate the sharpness of these predictions via simulations.

Published in at http://dx.doi.org/10.1214/13-AOS1162 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (3)

• Sparse permutation invariant covariance estimation
• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• Regularized rank-based estimation of high-dimensional nonparanormal graphical models

Cited by in corpus (7)

• Sparse and compositionally robust inference of microbial ecological networks
• Regularized estimation in sparse high-dimensional time series models
• Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
• Learning Graphs with Monotone Topology Properties and Multiple Connected Components
• Node-Centric Graph Learning from Data for Brain State Identification
• Estimation of dynamic networks for high-dimensional nonstationary time series
• Learning binary undirected graph in low dimensional regime