mlsanityData to 14 Oct 2026

Minima and Critical Points of the Bethe Free Energy Are Invariant Under Deformation Retractions of Factor Graphs

arXiv 2510.05380 ↗First posted 6 Oct 2025stat.ML cs.LG math.PRcited by 1

Not on the map. Why?

Abstract (arXiv)

In graphical models, factor graphs, and more generally energy-based models, the interactions between variables are encoded by a graph, a hypergraph, or, in the most general case, a partially ordered set (poset). Inference on such probabilistic models cannot be performed exactly due to cycles in the underlying structures of interaction. Instead, one resorts to approximate variational inference by optimizing the Bethe free energy. Critical points of the Bethe free energy correspond to fixed points of the associated Belief Propagation algorithm. A full characterization of these critical points for general graphs, hypergraphs, and posets with a finite number of variables is still an open problem. We show that, for hypergraphs and posets with chains of length at most 1, changing the poset of interactions of the probabilistic model to one with the same homotopy type induces a bijection between the critical points of the associated free energy. This result extends and unifies classical results that assume specific forms of collapsibility to prove uniqueness of the critical points of the Bethe free energy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 2 of its 26 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

2 of 26 references.

References · 2

  1. 2016Fixed Points of Belief Propagation -- An Analysis via Polynomial Homotopy Continuationcited by 4
  2. 2018Self-Guided Belief Propagation -- A Homotopy Continuation Methodcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.