On the free energy density of factor models on biregular graphs
Andr\'as M\'esz\'aros

TL;DR
This paper proves that for large girth sequences of biregular factor graphs, the free energy density converges and is accurately approximated by the Bethe-approximation, extending understanding of statistical mechanics on such graphs.
Contribution
It establishes the convergence of free energy density for large girth biregular factor graphs and confirms the Bethe-approximation as the limit.
Findings
Free energy density converges for large girth biregular graphs.
Bethe-approximation accurately predicts the limiting free energy.
Results apply to symmetric concave Hamiltonians.
Abstract
Let be a symmetric concave sequence. For a -biregular factor graph and , we define the Hamiltonian \[H_G(x)=\sum_{f\in F} h\left(\sum_{v\in \partial f} x_v\right),\] where is the set of variable nodes, is the set of factor nodes. We prove that if is a large girth sequence of -biregular factor graphs, then the free energy density of converges. The limiting free energy density is given by the Bethe-approximation.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Advanced Graph Theory Research · Stochastic processes and statistical mechanics
