Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Accuracy Bounds for Belief Propagation
Alexander Ihler
Abstract:
The belief propagation (BP) algorithm is widely applied to perform approximate infer- ence on arbitrary graphical models, in part due to its excellent empirical properties and performance. However, little is known theo- retically about when this algorithm will per- form well. Using recent analysis of conver- gence and stability properties in BP and new results on approximations in binary systems, we derive a bound on the error in BP's es- timates for pairwise Markov random fields over discrete{valued random variables. Our bound is relatively simple to compute, and compares favorably with a previous method of bounding the accuracy of BP.
Keywords:
Pages: 183-190
PS Link:
PDF Link: /papers/07/p183-ihler.pdf
BibTex:
@INPROCEEDINGS{Ihler07,
AUTHOR = "Alexander Ihler ",
TITLE = "Accuracy Bounds for Belief Propagation",
BOOKTITLE = "Proceedings of the Twenty-Third Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-07)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2007",
PAGES = "183--190"
}


hosted by DSL   •   site info   •   help