Uniformly Reweighted Belief Propagation: A Factor Graph Approach
Paper i proceeding, 2011

Tree-reweighted belief propagation is a message passing method that has certain advantages compared to traditional belief propagation (BP). However, it fails to outperform BP in a consistent manner, does not lend itself well to distributed implementation, and has not been applied to distributions with higher-order interactions. We propose a method called uniformly-reweighted belief propagation that mitigates these drawbacks. After having shown in previous works that this method can substantially outperform BP in distributed inference with pairwise interaction models, in this paper we extend it to higher-order interactions and apply it to LDPC decoding, leading performance gains over BP.

Författare

Henk Wymeersch

Signaler och system, Kommunikationssystem, informationsteori och antenner, Kommunikationssystem

Federico Penna

Politecnico di Torino

Vladimir Savic

Universidad Politecnica de Madrid

IEEE International Symposium on Information Theory - Proceedings

21578104 (ISSN)

2000-2004 6033905

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Telekommunikation

DOI

10.1109/ISIT.2011.6033905

ISBN

978-1-4577-0595-3