Moment Estimates and DeepRitz Methods on Learning Diffusion Systems with Non-gradient Drifts
Fanze Kong, Chen-Chih Lai, Yubin Lu
Published: 2025/8/31
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.