Uniformly Reweighted Belief Propagation: A Factor Graph Approach

Wymeersch, Henk, Penna, Federico and Savic, Vladimir (2011). Uniformly Reweighted Belief Propagation: A Factor Graph Approach. En: "2011 IEEE International Symposium on Information Theory Proceedings (ISIT)", 31/07/2011 - 05/08/2011, San Petersburgo, Rusia. ISBN 978-1-4577-0596-0.

Descripción

Título: Uniformly Reweighted Belief Propagation: A Factor Graph Approach
Autor/es:
  • Wymeersch, Henk
  • Penna, Federico
  • Savic, Vladimir
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: 2011 IEEE International Symposium on Information Theory Proceedings (ISIT)
Fechas del Evento: 31/07/2011 - 05/08/2011
Lugar del Evento: San Petersburgo, Rusia
Título del Libro: Proceedings of 2011 IEEE International Symposium on Information Theory Proceedings (ISIT)
Fecha: 2011
ISBN: 978-1-4577-0596-0
Materias:
ODS:
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[thumbnail of INVE_MEM_2011_94449.pdf]
Vista Previa
PDF (Portable Document Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (210kB) | Vista Previa

Resumen

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.

Más información

ID de Registro: 12197
Identificador DC: https://oa.upm.es/12197/
Identificador OAI: oai:oa.upm.es:12197
URL Oficial: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumb...
Depositado por: Memoria Investigacion
Depositado el: 30 Ago 2012 09:56
Ultima Modificación: 21 Abr 2016 11:24