On Hamilton-Jacobi equations and perceptron models

The solution to a finite-dimensional Hamilton-Jacobi equation is classically known to admit a variational representation in two situations: when the nonlinearity is convex or concave, by the Hopf-Lax formula; and when the initial condition is convex or concave, by the Hopf formula. We identify a third situation: the space variable is split into two groups of coordinates, the nonlinearity is the scalar product of the two corresponding partial gradients, and the initial condition is the sum of a convex function of the first group of coordinates and of an arbitrary Lipschitz function of the second group. This structure is precisely that of the Hamilton-Jacobi equations describing the limit free energy of perceptron models. We illustrate this point by identifying the limit free energy of a class of perceptron models that can be rewritten as bipartite spin glasses, with Ising spins in one layer and bounded soft spins in the other. We also discuss how to extend the approach to several other classes of models, including general Ising and spherical perceptrons, possibly with labelled patterns.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20870
Primary Topic
Nonlinear Partial Differential Equations
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

On Hamilton-Jacobi equations and perceptron models

Jean-Christophe Mourrat, Hong-Bin Chen
arXiv (Cornell University)
Nonlinear Partial Differential Equations
preprint

On Hamilton-Jacobi equations and perceptron models

Jean-Christophe Mourrat, Hong-Bin Chen
preprint en

Abstract

The solution to a finite-dimensional Hamilton-Jacobi equation is classically known to admit a variational representation in two situations: when the nonlinearity is convex or concave, by the Hopf-Lax formula; and when the initial condition is convex or concave, by the Hopf formula. We identify a third situation: the space variable is split into two groups of coordinates, the nonlinearity is the scalar product of the two corresponding partial gradients, and the initial condition is the sum of a convex function of the first group of coordinates and of an arbitrary Lipschitz function of the second group. This structure is precisely that of the Hamilton-Jacobi equations describing the limit free energy of perceptron models. We illustrate this point by identifying the limit free energy of a class of perceptron models that can be rewritten as bipartite spin glasses, with Ising spins in one layer and bounded soft spins in the other. We also discuss how to extend the approach to several other classes of models, including general Ising and spherical perceptrons, possibly with labelled patterns.

arXiv (Cornell University)
Nonlinear Partial Differential Equations
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon