Graphical Models and Exponential Families

by   Dan Geiger, et al.

We provide a classification of graphical models according to their representation as subfamilies of exponential families. Undirected graphical models with no hidden variables are linear exponential families (LEFs), directed acyclic graphical models and chain graphs with no hidden variables, including Bayesian networks with several families of local distributions, are curved exponential families (CEFs) and graphical models with hidden variables are stratified exponential families (SEFs). An SEF is a finite union of CEFs satisfying a frontier condition. In addition, we illustrate how one can automatically generate independence and non-independence constraints on the distributions over the observable variables implied by a Bayesian network with hidden variables. The relevance of these results for model selection is examined.


page 1

page 2

page 4

page 5

page 9


Staged trees are curved exponential families

Staged tree models are a discrete generalization of Bayesian networks. W...

Total positivity in structured binary distributions

We study binary distributions that are multivariate totally positive of ...

Probabilistic Dependency Graphs

We introduce Probabilistic Dependency Graphs (PDGs), a new class of dire...

Stratified Graphical Models - Context-Specific Independence in Graphical Models

Theory of graphical models has matured over more than three decades to p...

Learning Continuous Exponential Families Beyond Gaussian

We address the problem of learning of continuous exponential family dist...

On the Geometry of Bayesian Graphical Models with Hidden Variables

In this paper we investigate the geometry of the likelihood of the unkno...