Change search
ReferencesLink to record
Permanent link

Direct link
Uniformly reweighted belief propagation: A factor graph approach
Chalmers University of Technology, Sweden.
Politecnico di Torino, Italy.
Technical University of Madrid, Spain. (Signal Processing Applications Group)
2011 (English)In: Proc. of IEEE Intl. Symp. on Information Theory Proceedings (ISIT), 2011, 2000-2004 p.Conference paper, Presentation (Refereed)
Abstract [en]

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.

Place, publisher, year, edition, pages
2011. 2000-2004 p.
Keyword [en]
Belief propagation, Bit error rate, Decoding, Graphical models, Markov processes, Message passing, LDPC codes
National Category
Engineering and Technology Signal Processing Communication Systems
URN: urn:nbn:se:liu:diva-81417DOI: 10.1109/ISIT.2011.6033905ISBN: 978-1-4577-0596-0OAI: diva2:552304
IEEE Intl. Symp. on Information Theory Proceedings (ISIT), St. Petersburg, Russia
Available from: 2012-09-13 Created: 2012-09-13 Last updated: 2012-09-21

Open Access in DiVA

fulltext(261 kB)252 downloads
File information
File name FULLTEXT01.pdfFile size 261 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textUniformly reweighted belief propagation: A factor graph approach

Search in DiVA

By author/editor
Savic, Vladimir
Engineering and TechnologySignal ProcessingCommunication Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 252 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 147 hits
ReferencesLink to record
Permanent link

Direct link