The Bethe Partition Function of Log-supermodular Graphical Models

Details The Bethe Partition Function of Log-supermodular Graphical Models The Bethe Partition Function of Log-supermodular Graphical Models

2012-02-27

arxiv.org/abs/1202.6035v2

Computer Science

Discrete Mathematics

Typo, bug fixes, and improved exposition

Scientific paper

Sudderth, Wainwright, and Willsky have conjectured that the Bethe approximation corresponding to any fixed point of the belief propagation algorithm over an attractive, pairwise binary graphical model provides a lower bound on the true partition function. In this work, we resolve this conjecture in the affirmative by demonstrating that, for any graphical model with binary variables whose potential functions (not necessarily pairwise) are all log-supermodular, the Bethe partition function always lower bounds the true partition function. The proof of this result follows from a new variant of the "four functions" theorem that may be of independent interest.

Affiliated with

Also associated with

No associations

Rating

The Bethe Partition Function of Log-supermodular Graphical Models 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 The Bethe Partition Function of Log-supermodular Graphical Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Bethe Partition Function of Log-supermodular Graphical Models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-264197