Spectral Bounds for the Ising Ferromagnet on an Arbitrary Given Graph
Alaa Saade, Florent Krzakala, Lenka Zdeborov\'a

TL;DR
This paper develops efficient spectral bounds for the Ising ferromagnet on any finite graph, enabling rigorous upper bounds on key quantities like the partition function, magnetizations, and correlations using high-temperature expansions and spectral operators.
Contribution
It introduces a novel method to use classical bounds with spectral operators for arbitrary graphs, improving the analysis of the Ising model in high-temperature regimes.
Findings
Spectral bounds effectively upper-bound the partition function and correlations.
Susceptibility propagation converges and bounds correlations in high-temperature regions.
Method applies to graphs with arbitrary topology and positive couplings.
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.
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.
