• DocumentCode
    1866355
  • Title

    Comments on Why Generalized BP Serves So Remarkably in 2-D Channels

  • Author

    Shental, Ori ; Shental, Noam ; Shamai, Shlomo ; Kanter, Ido ; Weiss, Anthony J. ; Weiss, Yair

  • Author_Institution
    Univ. of California, San Diego
  • fYear
    2007
  • fDate
    Jan. 29 2007-Feb. 2 2007
  • Firstpage
    369
  • Lastpage
    369
  • Abstract
    Generalized belief propagation (GBP) algorithm has been shown recently to infer the a-posteriori probabilities of finite-state input two-dimensional (2D) Gaussian channels with memory in a practically accurate manner, thus enabling near-optimal estimation of the transmitted symbols and the Shannon-theoretic information rates. In this note, a rationalization of this excellent performance of GBP is addressed.
  • Keywords
    Gaussian channels; belief networks; channel estimation; 2D Gaussian channels; GBP algorithm; Shannon-theoretic information rates; a-posteriori probabilities; generalized belief propagation algorithm; AWGN; Belief propagation; Gaussian channels; Graphical models; Information rates; Interference; Message passing; Nearest neighbor searches; Probability; Two dimensional displays;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Theory and Applications Workshop, 2007
  • Conference_Location
    La Jolla, CA
  • Print_ISBN
    978-0-615-15314-8
  • Type

    conf

  • DOI
    10.1109/ITA.2007.4357604
  • Filename
    4357604