Guerra Interpolation and Optimal Transport: Kantorovich Bounds, Brenier Maps and the Replicon
Elena Agliari, Adriano Barra, Andrea Ladiana, Andrea Lepre, Diego Pallara
cond-mat.dis-nn
Nov 13, 2026 · v1
math.AP math.PR
TL;DR
All numbered theorems, propositions and lemmas are formalized in Lean 4 with Mathlib in the GuerraHJ library: 7,891 lines, 519 results, no sorry.
Abstract
Since Guerra's work, mean-field spin glasses have been studied through Hamilton–Jacobi equations. Here, using the Curie–Weiss and the Sherrington–Kirkpatrick models as prototypical examples, we show that his celebrated interpolation method is itself an optimal transport computation. After a linear change of variables the finite-$N$ pressure becomes an action $u$ with $\partial_t u = -A/2$ and $\partial_x u = -B$, where $B^2 \le A$, so $u$ is a classical subsolution of $\partial_t u+\frac12(\partial_x u)^2 \le 0$. Integrating along a straight segment gives Guerra's sum rule, and dropping its remainder makes $u(0,\cdot)$ and $u(t,\cdot)$ an admissible pair for the dual Kantorovich problem with quadratic cost. For the Curie–Weiss model and $t > 0$, $T_t(y) = y-t\tanh y$ is an optimal transport map from every source with finite first moment if and only if $t \le 1$, and the Kantorovich potentials are the limiting pressures. For the replica-symmetric Sherrington–Kirkpatrick model, the cavity map is injective on the physical half-line and the curvature of its Brenier potential is the longitudinal eigenvalue, which exceeds the replicon eigenvalue $Λ_{\mathrm{AT}}$: transport of Dirac masses does not detect the de Almeida–Thouless line. The replicon appears along the $\mathcal{W}_2$ geodesic that splits a Dirac mass into two atoms, as the second variation of a second-order surrogate of the two-atom Parisi functional. From a Dirac initial datum, Guerra's $K$-step bound takes Hopf–Lax form, and the Parisi formula becomes a Hopf–Lax formula over atomic measures. With a $\mathcal{W}_1$-Lipschitz bound for its initial datum, proved by comparing Cole–Hopf layers, we let $K\to\infty$ and recover at Dirac data the Hopf–Lax form of the Parisi formula due to Mourrat and to Mourrat and Panchenko, with a rate for equal-mass approximations.
Problem
Guerra's interpolation method for mean-field spin glasses (Curie–Weiss and Sherrington–Kirkpatrick models) is known to connect to Hamilton–Jacobi equations. Its relation to optimal transport, and to the de Almeida–Thouless instability, had not been made explicit.
Approach
After a linear change of variables, the finite-N pressure becomes a classical subsolution of the inviscid Hamilton–Jacobi equation. Guerra's sum rule along a segment then yields admissible pairs for the dual Kantorovich problem with quadratic cost. Brenier maps, Wasserstein geodesics that split a Dirac mass, and K-step replica symmetry breaking bounds are analyzed in Hopf–Lax form. All numbered statements are machine-checked in Lean 4 with Mathlib; general measures are represented via quantile functions.
Results
For Curie–Weiss, T_t(y)=y−t tanh y is optimal if and only if t≤1. For replica-symmetric SK, transport of Dirac masses does not detect the AT line, and the replicon appears as a Wasserstein second variation. Letting K→∞ recovers the Mourrat–Panchenko Hopf–Lax form of the Parisi formula at Dirac data, with a rate for equal-mass approximations. The Lean library spans 18 modules with no sorry.