Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Out-of-equilibrium dynamical mean-field equations for the perceptron model

Abstract : Perceptrons are the building blocks of many theoretical approaches to a wide range of complex systems, ranging from neural networks and deep learning machines, to constraint satisfaction problems, glasses and ecosystems. Despite their applicability and importance, a detailed study of their Langevin dynamics has never been performed yet. Here we derive the mean-field dynamical equations that describe the continuous random perceptron in the thermodynamic limit, in a very general setting with arbitrary noise and friction kernels, not necessarily related by equilibrium relations. We derive the equations in two ways: via a dynamical cavity method, and via a path-integral approach in its supersymmetric formulation. The end point of both approaches is the reduction of the dynamics of the system to an effective stochastic process for a representative dynamical variable. Because the perceptron is formally very close to a system of interacting particles in a high dimensional space, the methods we develop here can be transferred to the study of liquid and glasses in high dimensions. Potentially interesting applications are the study of the glass transition in active matter, the study of the dynamics around the jamming transition, and the calculation of rheological properties in driven systems.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [41 references]  Display  Hide  Download
Contributor : Emmanuelle de Laborderie Connect in order to contact the contributor
Submitted on : Friday, January 12, 2018 - 4:04:23 PM
Last modification on : Friday, October 15, 2021 - 1:41:14 PM
Long-term archiving on: : Monday, May 7, 2018 - 5:34:11 PM


Files produced by the author(s)


  • HAL Id : cea-01682940, version 1


Elisabeth Agoritsas, Giulio Biroli, Pierfrancesco Urbani, Francesco Zamponi. Out-of-equilibrium dynamical mean-field equations for the perceptron model. 2018. ⟨cea-01682940⟩



Record views


Files downloads