Structure-Aware Variational Learning of a Class of Generalized Diffusions

ArXi:2604.20188v1 Announce Type: new Learning the underlying potential energy of stochastic gradient systems from partial and noisy observations is a fundamental problem arising in physics, chemistry, and data-driven modeling. Classical approaches often rely on direct regression of governing equations or velocity fields, which can be sensitive to noise and external perturbations and may fail when observations are incomplete.