Score: 1

Moment Estimate and Variational Approach for Learning Generalized Diffusion with Non-gradient Structures

Published: August 3, 2025 | arXiv ID: 2508.01854v2

By: Fanze Kong, Chen-Chih Lai, Yubin Lu

BigTech Affiliations: University of Washington

Potential Business Impact:

Finds hidden rules in how things move.

This paper proposes a data-driven learning framework for identifying governing laws of generalized diffusions with non-gradient components. By combining energy dissipation laws with a physically consistent penalty and first-moment evolution, we design a two-stage method to recover the pseudo-potential and rotation in the pointwise orthogonal decomposition of a class of non-gradient drifts in generalized diffusions. Our two-stage method is applied to complex generalized diffusion processes including dissipation-rotation dynamics, rough pseudo-potentials and noisy data. Representative numerical experiments demonstrate the effectiveness of our approach for learning physical laws in non-gradient generalized diffusions.

Country of Origin
🇺🇸 United States

Page Count
16 pages

Category
Physics:
Computational Physics