Belief Propagation on replica symmetric random factor graph models

Amin Coja-Oghlan, Will Perkins

Research output: Contribution to journalArticlepeer-review

138 Downloads (Pure)

Abstract

According to physics predictions, the free energy of random factor graph
models that satisfy a certain “static replica symmetry” condition can be
calculated via the Belief Propagation message passing scheme [Krzakala
et al., PNAS 2007]. Here we prove this conjecture for two general classes of
random factor graph models, namely Poisson random factor graphs and
random regular factor graphs. Specifically, we show that the messages
constructed just as in the case of acyclic factor graphs asymptotically satisfy
the Belief Propagation equations and that the free energy density is
given by the Bethe free energy formula.
Original languageEnglish
JournalAnnales de L'Institut Henri Poincare (D)
Early online date9 May 2017
Publication statusE-pub ahead of print - 9 May 2017

Fingerprint

Dive into the research topics of 'Belief Propagation on replica symmetric random factor graph models'. Together they form a unique fingerprint.

Cite this