English

Simulation-Free Differential Dynamics through Neural Conservation Laws

Machine Learning 2025-06-24 v1 Artificial Intelligence

Abstract

We present a novel simulation-free framework for training continuous-time diffusion processes over very general objective functions. Existing methods typically involve either prescribing the optimal diffusion process -- which only works for heavily restricted problem formulations -- or require expensive simulation to numerically obtain the time-dependent densities and sample from the diffusion process. In contrast, we propose a coupled parameterization which jointly models a time-dependent density function, or probability path, and the dynamics of a diffusion process that generates this probability path. To accomplish this, our approach directly bakes in the Fokker-Planck equation and density function requirements as hard constraints, by extending and greatly simplifying the construction of Neural Conservation Laws. This enables simulation-free training for a large variety of problem formulations, from data-driven objectives as in generative modeling and dynamical optimal transport, to optimality-based objectives as in stochastic optimal control, with straightforward extensions to mean-field objectives due to the ease of accessing exact density functions. We validate our method in a diverse range of application domains from modeling spatio-temporal events to learning optimal dynamics from population data.

Keywords

Cite

@article{arxiv.2506.18604,
  title  = {Simulation-Free Differential Dynamics through Neural Conservation Laws},
  author = {Mengjian Hua and Eric Vanden-Eijnden and Ricky T. Q. Chen},
  journal= {arXiv preprint arXiv:2506.18604},
  year   = {2025}
}
R2 v1 2026-07-01T03:29:23.894Z