Factorization of discrete probability distributions

  • Authors:

  • Dan Geiger;Christopher Meek;Bernd Sturmfels

  • Affiliations:

  • Computer Science Department, Technion, Haifa, Israel;Microsoft Research, Microsoft Cooperation, Redmond, WA;Department of Mathematics, University of California Berkeley, Berkeley, CA

  • Venue:
  • UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.