English

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}
}
R2 v1 2026-07-01T05:33:57.786Z