Factorization of Discrete Probability Distributions

12/12/2012

∙

by   Dan Geiger, et al.

∙

0

∙

share

We formulate necessary and sufficient conditions for an arbitrary discrete probability distribution to factor according to an undirected graphical model, or a log-linear model, or other more general exponential models. This result generalizes the well known Hammersley-Clifford Theorem.