paper-with-me

Papers

Identifiable learning of dissipative dynamics

2025-10-28 · Aiqing Zhu, Beatrice W. Soh, Grigorios A. Pavliotis, Qianxiao Li arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.24160

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning

2020-02-20 · ICLR Workshop DeepDiffEq 2019 12 · Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty

In this work, we introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To improve prediction accuracy while reduc…

Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately

2022-01-25 · Andrew Sosanya, Sam Greydanus

Understanding natural symmetries is key to making sense of our complex and ever-changing world. Recent work has shown that neural networks can learn such symmetries directly from data using Hamiltonian Neural Networks (H…

Friction

Learning dissipative Hamiltonian dynamics with reproducing kernel Hilbert spaces and random Fourier features

2024-10-24 · Torbjørn Smith, Olav Egeland

This paper presents a new method for learning dissipative Hamiltonian dynamics from a limited and noisy dataset. The method uses the Helmholtz decomposition to learn a vector field as the sum of a symplectic and a dissip…

The Underlying Dynamics of Life and Its Evolution: A Prigogine-Inspired Informational Dissipative System

2024-12-03 · Salvatore Chirumbolo, Antonio Vella

Life is fundamentally a scientific enigma. The interplay between chaos, entropy dynamics, and Prigogine's dissipative systems offers profound insights into the emergence, stabilization, and eventual collapse of far-from-…

Learning Deep Dissipative Dynamics

2024-08-21 · Yuji Okamoto, Ryosuke Kojima

This study challenges strictly guaranteeing ``dissipativity'' of a dynamical system represented by neural networks learned from given time-series data. Dissipativity is a crucial indicator for dynamical systems that gene…

LEMMATime Seriesvalid