Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization

Details Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization

2012-02-14

arxiv.org/abs/1202.3777v1

Computer Science

Artificial Intelligence

Scientific paper

Compiling Bayesian networks (BNs) to junction trees and performing belief propagation over them is among the most prominent approaches to computing posteriors in BNs. However, belief propagation over junction tree is known to be computationally intensive in the general case. Its complexity may increase dramatically with the connectivity and state space cardinality of Bayesian network nodes. In this paper, we address this computational challenge using GPU parallelization. We develop data structures and algorithms that extend existing junction tree techniques, and specifically develop a novel approach to computing each belief propagation message in parallel. We implement our approach on an NVIDIA GPU and test it using BNs from several applications. Experimentally, we study how junction tree parameters affect parallelization opportunities and hence the performance of our algorithm. We achieve speedups ranging from 0.68 to 9.18 for the BNs studied.

Affiliated with

Also associated with

No associations

Rating

Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Belief Propagation by Message Passing in Junction Trees: Computing Each Message Faster Using GPU Parallelization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-90776