Spectral Bounds for the Ising Ferromagnet on an Arbitrary Given Graph

Abstract

We revisit classical bounds of M. E. Fisher on the ferromagnetic Ising model, and show how to efficiently use them on an arbitrary given graph to rigorously upper-bound the partition function, magnetizations, and correlations. The results are valid on any finite graph, with arbitrary topology and arbitrary positive couplings and fields. Our results are based on high temperature expansions of the aforementioned quantities, and are expressed in terms of two related linear operators: the non-backtracking operator and the Bethe Hessian. As a by-product, we show that in a well-defined high-temperature region, the susceptibility propagation algorithm converges and provides an upper bound on the true spin-spin correlations.

17 pages, 1 figure

References in corpus (5)

• Loop series for discrete statistical models on graphs
• Efficient Exact Inference in Planar Ising Models
• Clustering from Sparse Pairwise Measurements
• Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation
• Non-backtracking operator for Ising model and its application in attractor neural networks