On Graphical Models via Univariate Exponential Family Distributions

Abstract

Undirected graphical models, or Markov networks, are a popular class of statistical models, used in a wide variety of applications. Popular instances of this class include Gaussian graphical models and Ising models. In many settings, however, it might not be clear which subclass of graphical models to use, particularly for non-Gaussian and non-categorical data. In this paper, we consider a general sub-class of graphical models where the node-wise conditional distributions arise from exponential families. This allows us to derive multivariate graphical model distributions from univariate exponential family distributions, such as the Poisson, negative binomial, and exponential distributions. Our key contributions include a class of M-estimators to fit these graphical model distributions; and rigorous statistical analysis showing that these M-estimators recover the true graphical model structure exactly, with high probability. We provide examples of genomic and proteomic networks learned via instances of our class of graphical models derived from Poisson and exponential distributions.

Journal of Machine Learning Research

References in corpus (5)

• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• Copula Gaussian graphical models and their application to modeling functional disability data
• Stability Approach to Regularization Selection (StARS) for High Dimensional Graphical Models
• Sparse inverse covariance estimation with the lasso
• The Nonparanormal SKEPTIC

Cited by in corpus (15)

• mgm: Estimating Time-Varying Mixed Graphical Models in High-Dimensional Data
• Learning Large-Scale Bayesian Networks with the sparsebn Package
• Concentration and consistency results for canonical and curved exponential-family models of random graphs
• On Semiparametric Exponential Family Graphical Models
• Learning Mixed Graphical Models
• A General Framework for Mixed Graphical Models
• Selection and Estimation for Mixed Graphical Models
• High Dimensional Semiparametric Latent Graphical Model for Mixed Data
• Partially Linear Additive Gaussian Graphical Models
• Network Clustering for Latent State and Changepoint Detection
• Selective Inference and Learning Mixed Graphical Models
• Measurement error and reliability from a different perspective: Reliability of decision functions and the sum score
• Learning Pairwise Graphical Models with Nonlinear Sufficient Statistics
• Coresets for Dependency Networks
• Inferring network structure in non-normal and mixed discrete-continuous genomic data