Independence of Causal Influence and Clique Tree Propagation

2013/02/06 by Nevin Lianwen Zhang, Li Yan, Zhang, Nevin Lianwen +1
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #cs.AI

paper · pdf · doi:10.48550/arxiv.1302.1574

Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)

arxiv created 2013/02/06 · arxiv updated 2013/02/08

Abstract

This paper explores the role of independence of causal influence (ICI) in Bayesian network inference. ICI allows one to factorize a conditional probability table into smaller pieces. We describe a method for exploiting the factorization in clique tree propagation (CTP) - the state-of-the-art exact inference algorithm for Bayesian networks. We also present empirical results showing that the resulting algorithm is significantly more efficient than the combination of CTP and previous techniques for exploiting ICI.

Related

• Inter-causal Independence and Heterogeneous Factorization
• Surjective Independence of Causal Influences for Local Bayesian Network Structures
• Exploiting Functional Dependence in Bayesian Network Inference
• Lazy Propagation in Junction Trees
• A Bayesian Approach to Learning Causal Networks