A Scheme for Approximating Probabilistic Inference

This paper describes a class ofprobabilistic approximation algorithms based on bucket elimination which o er adjustable levels of accuracy ande ciency. We analyzethe approximation for several tasks: nding the most probable explanation, belief updating and nding the maximum a posteriori hypothesis. We identify regions of completeness and provide preliminary empirical evaluation on randomly generated networks. 1 Overview Bucket elimination, is a unifying algorithmic framework that generalizes dynamic programming to enable many complex problem-solving and reasoning activities. Among the algorithms that can be accommodated within this framework are directional resolution for propositional satis ability, adaptive consistency for constraint satisfaction, Fourier and Gaussian elimination for linear equalities and inequalities, and dynamic programming for combinatorial optimization 7 . Many algorithms for probabilistic inference, such as belief updating, nding the most probable explanation, n...

• Type: Conference
• Year: 1997
• Where: UAI
• Authors: Rina Dechter, Irina Rish
• Keywords: Algorithm, Bucket Elimination, Posteriori Hypothesis, UAI 1997, UAI 2008