Hypergraph Counting and Mixed $p$-Spin Glass Models under Replica Symmetry

TL;DR

This paper analyzes high-temperature fluctuations in mixed p-spin glass models using hypergraph counting, revealing multiple phase transitions, new critical temperatures, and differences between even and odd p-spin structures.

Contribution

It extends cluster expansion methods to mixed p-spin models, uncovering multiple transition phenomena and providing explicit convergence rates and structural insights.

Findings

Identifies multiple transition phenomena in mixed p-spin models.

Derives a new critical inverse temperature from second moment estimates.

Shows differences in cluster structures between even and odd p-spin models.

Abstract

We study the fluctuation problems at high temperature in the general mixed $p$-spin glass models under the weak external field assumption: $h= \rho N^{-\alpha}, \rho>0, \alpha \in [1/4,\infty]$. By extending the cluster expansion approach to this generic setting, we convert the fluctuation problem as a hypergraph counting problem and thus obtain a new multiple-transition phenomenon. A by-product of our results is a new critical inverse temperature obtained from optimal second moment estimates. In particular, all our fluctuation results hold up to the threshold. Combining with multivariate Stein's method, we also obtain an explicit convergence rate under proper moment assumptions on the general symmetric disorder. Our results have several further implications. First, our approach works for both even and odd pure $p$-spin models. The leading cluster structures in the odd $p$ case are different and more involved than in the even $p$ case. This combinatorially explains the folklore that odd $p$-spin is more complicated than even $p$. Second, in the mixed $p$-spin setting, the cluster structures differ depending on the relation between the minimum effective even and odd $p$-spins: $p_e$ and $p_o$. As an example, at $h=0$, there are three sub-regimes: $p_e<p_o, p_o<p_e<2p_o, p_e\ge 2p_o$, wherein the first and third ones, the mixed model behaves essentially like a pure $p$-spin model, and only in the second regime, it is more like a mixture. This gives another criterion for classifying mean-field spin glass models compared to the work of Auffinger and Ben Arous (Ann.~Probab.~41 (2013), no.~6, 4214--4247), where the idea is based on complexity computations for spherical models. Third, our framework naturally implies a multi-scale fluctuation phenomenon conjectured in the work of Bovier and Schertzer (Probab. Theory Relat. Fields (2024)).