Moment Estimates and DeepRitz Methods on Learning Diffusion Systems with Non-gradient Drifts
Machine Learning
2025-09-16 v1 Computational Physics
Abstract
Conservative-dissipative dynamics are ubiquitous across a variety of complex open systems. We propose a data-driven two-phase method, the Moment-DeepRitz Method, for learning drift decompositions in generalized diffusion systems involving conservative-dissipative dynamics. The method is robust to noisy data, adaptable to rough potentials and oscillatory rotations. We demonstrate its effectiveness through several numerical experiments.
Keywords
Cite
@article{arxiv.2509.10495,
title = {Moment Estimates and DeepRitz Methods on Learning Diffusion Systems with Non-gradient Drifts},
author = {Fanze Kong and Chen-Chih Lai and Yubin Lu},
journal= {arXiv preprint arXiv:2509.10495},
year = {2025}
}