Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Loopy Belief Propogation and Gibbs Measures
Sekhar Tatikonda, Michael Jordan
Abstract:
We address the question of convergence in the loopy belief propagation (LBP) algorithm. Specifically, we relate convergence of LBP to the existence of a weak limit for a sequence of Gibbs measures defined on the LBP s associated computation tree.Using tools FROM the theory OF Gibbs measures we develop easily testable sufficient conditions FOR convergence.The failure OF convergence OF LBP implies the existence OF multiple phases FOR the associated Gibbs specification.These results give new insight INTO the mechanics OF the algorithm.
Keywords:
Pages: 493-500
PS Link:
PDF Link: /papers/02/p493-tatikonda.pdf
BibTex:
@INPROCEEDINGS{Tatikonda02,
AUTHOR = "Sekhar Tatikonda and Michael Jordan",
TITLE = "Loopy Belief Propogation and Gibbs Measures",
BOOKTITLE = "Proceedings of the Eighteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-02)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2002",
PAGES = "493--500"
}


hosted by DSL   •   site info   •   help