Reading Dependencies from Polytree-Like Bayesian Networks

Abstract

We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictive.

Appears in Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007)

References in corpus (4)

• Learning the Structure of Dynamic Probabilistic Networks
• Strong Completeness and Faithfulness in Bayesian Networks
• Finding Optimal Bayesian Networks
• Perfect Tree-Like Markovian Distributions