• Media type: Text; E-Article; Electronic Conference Proceeding
  • Title: Harnessing the Bethe Free Energy
  • Contributor: Bapst, Victor [Author]; Coja-Oghlan, Amin [Author]
  • Published: Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2015
  • Language: English
  • DOI: https://doi.org/10.4230/LIPIcs.APPROX-RANDOM.2015.467
  • Keywords: free energy ; Gibbs measure ; Belief Propagation ; partition function
  • Origination:
  • Footnote: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Description: Gibbs measures induced by random factor graphs play a prominent role in computer science, combinatorics and physics. A key problem is to calculate the typical value of the partition function. According to the "replica symmetric cavity method", a heuristic that rests on non-rigorous considerations from statistical mechanics, in many cases this problem can be tackled by way of maximising a functional called the "Bethe free energy". In this paper we prove that the Bethe free energy upper-bounds the partition function in a broad class of models. Additionally, we provide a sufficient condition for this upper bound to be tight.
  • Access State: Open Access