Computer Science – Information Theory
Scientific paper
2010-02-17
Computer Science
Information Theory
Reformatted, corrected technical and non-technical errors, extended sections, and removed the applications sections.
Scientific paper
The max-product algorithm, which attempts to compute the maximizing assignment of a given objective function, has recently found applications in quadratic minimization and combinatorial optimization. Unfortunately, the max-product algorithm is not guaranteed to converge and, even if it does, is not guaranteed to produce the optimal assignment. In this work, we provide a simple derivation of a new family of message passing algorithms. We first show how to arrive at this general message passing scheme by "splitting" the factors of our graphical model, and then we demonstrate that this construction can be extended beyond integral splitting. We prove that, for any objective function that attains its maximum value over its domain, this new family of message passing algorithms always contains a message passing scheme that guarantees correctness upon convergence to a unique estimate. Finally, we adopt an asynchronous message passing schedule and prove that, under mild assumptions, such a schedule guarantees the convergence of our algorithm.
Ruozzi Nicholas
Tatikonda Sekhar
No associations
LandOfFree
Convergent and Correct Message Passing Schemes for Optimization Problems over 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 Convergent and Correct Message Passing Schemes for Optimization Problems over Graphical Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convergent and Correct Message Passing Schemes for Optimization Problems over Graphical Models will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-51837