AAAI Publications, The Twenty-Ninth International Flairs Conference

Font Size: 
Testing Independencies in Bayesian Networks with i-Separation
Cory J. Butz, André E. dos Santos, Jhonatan S. Oliveira, Christophe Gonzales

Last modified: 2016-03-30

Abstract


Testing independencies in Bayesian networks (BNs) is a fundamental task in probabilistic reasoning. In this paper, we propose inaugural-separation (i-separation) as a new method for testing independencies in BNs. We establish the correctness of i-separation. Our method has several theoretical and practical advantages. There are at least five ways in which i-separation is simpler than d-separation, the classical method for testing independencies in BNs, of which the most important is that "blocking" works in an intuitive fashion. In practice, our empirical evaluation shows that i-separation tends to be faster than d-separation in large BNs.

Keywords


Bayesian networks; independencies; d-separation

Full Text: PDF