Equilibrium Propagation for Learning in Lagrangian Dynamical Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Massar, Serge
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909694518362112
author Massar, Serge
author_facet Massar, Serge
contents We propose a method for training dynamical systems governed by Lagrangian mechanics using Equilibrium Propagation. Our approach extends Equilibrium Propagation - initially developed for energy-based models - to dynamical trajectories by leveraging the principle of action extremization. Training is achieved by gently nudging trajectories toward desired targets and measuring how the variables conjugate to the parameters to be trained respond. This method is particularly suited to systems with periodic boundary conditions or fixed initial and final states, enabling efficient parameter updates without requiring explicit backpropagation through time. In the case of periodic boundary conditions, this approach yields the semiclassical limit of Quantum Equilibrium Propagation. Applications to systems with dissipation are also discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Equilibrium Propagation for Learning in Lagrangian Dynamical Systems
Massar, Serge
Chaotic Dynamics
Machine Learning
Data Analysis, Statistics and Probability
We propose a method for training dynamical systems governed by Lagrangian mechanics using Equilibrium Propagation. Our approach extends Equilibrium Propagation - initially developed for energy-based models - to dynamical trajectories by leveraging the principle of action extremization. Training is achieved by gently nudging trajectories toward desired targets and measuring how the variables conjugate to the parameters to be trained respond. This method is particularly suited to systems with periodic boundary conditions or fixed initial and final states, enabling efficient parameter updates without requiring explicit backpropagation through time. In the case of periodic boundary conditions, this approach yields the semiclassical limit of Quantum Equilibrium Propagation. Applications to systems with dissipation are also discussed.
title Equilibrium Propagation for Learning in Lagrangian Dynamical Systems
topic Chaotic Dynamics
Machine Learning
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2505.07363