Global Conditioning for Probabilistic Inference in Belief Networks
This work addresses inference efficiency for researchers in probabilistic graphical models, offering incremental improvements by integrating and extending prior techniques.
The paper tackles probabilistic inference in belief networks by proposing global conditioning as a generalization of loop-cutset conditioning, showing it enables parallel processing and time-memory tradeoffs while unifying existing methods into a cohesive framework.
In this paper we propose a new approach to probabilistic inference on belief networks, global conditioning, which is a simple generalization of Pearl's (1986b) method of loopcutset conditioning. We show that global conditioning, as well as loop-cutset conditioning, can be thought of as a special case of the method of Lauritzen and Spiegelhalter (1988) as refined by Jensen et al (199Oa; 1990b). Nonetheless, this approach provides new opportunities for parallel processing and, in the case of sequential processing, a tradeoff of time for memory. We also show how a hybrid method (Suermondt and others 1990) combining loop-cutset conditioning with Jensen's method can be viewed within our framework. By exploring the relationships between these methods, we develop a unifying framework in which the advantages of each approach can be combined successfully.