d-Separation: From Theorems to Algorithms
Artificial Intelligence
2013-04-08 v1
Abstract
An efficient algorithm is developed that identifies all independencies implied by the topology of a Bayesian network. Its correctness and maximality stems from the soundness and completeness of d-separation with respect to probability theory. The algorithm runs in time O (l E l) where E is the number of edges in the network.
Cite
@article{arxiv.1304.1505,
title = {d-Separation: From Theorems to Algorithms},
author = {Dan Geiger and Tom S. Verma and Judea Pearl},
journal= {arXiv preprint arXiv:1304.1505},
year = {2013}
}
Comments
Appears in Proceedings of the Fifth Conference on Uncertainty in Artificial Intelligence (UAI1989)