Identifiable learning of dissipative dynamics

TL;DR

This paper presents a neural framework for learning and interpreting dissipative stochastic dynamics from data, enabling the quantification of irreversibility and energy landscapes in complex non-equilibrium systems.

Contribution

It introduces a universal, identifiable neural method that learns energy landscapes and separates reversible from irreversible dynamics, providing insights into non-equilibrium behavior.

Findings

Identifies a unique energy landscape for dissipative systems.

Separates reversible and irreversible motion from trajectory data.

Reveals super-linear barrier scaling and suppression of irreversibility with batch size.

Abstract

Complex dissipative systems appear across science and engineering, from polymers and active matter to learning algorithms. These systems operate far from equilibrium, where energy dissipation and time irreversibility govern their behavior but are difficult to quantify from data. Here, we introduce a universal and identifiable neural framework that learns dissipative stochastic dynamics directly from trajectories while ensuring interpretability, expressiveness, and uniqueness. Our method identifies a unique energy landscape, separates reversible from irreversible motion, and allows direct computation of the entropy production, providing a principled measure of irreversibility and deviations from equilibrium. Applications to polymer stretching in elongational flow and to stochastic gradient Langevin dynamics reveal new insights, including super-linear scaling of barrier heights and sub-linear scaling of entropy production rates with the strain rate, and the suppression of irreversibility with increasing batch size. Our methodology thus establishes a general, data-driven framework for discovering and interpreting non-equilibrium dynamics.