发表机构
University of Washington; Hunan University(华盛顿大学; 湖南大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出一种结合蒙特卡洛弱监督、能量变分物理约束和拟牛顿精化的深度学习框架,用于高维稳态Fokker-Planck方程,数值实验验证了其在粗糙势和噪声数据下的准确性与稳健性。
AI 中文摘要
本文开发了一个深度学习框架,通过结合蒙特卡洛弱监督、能量变分物理约束和拟牛顿精化,求解高维稳态Fokker-Planck方程。蒙特卡洛统计量锚定稳态密度的尺度,而自由能变分损失则强制执行平衡物理;该公式还适用于具有逐点正交旋转分量的稳态系统,并且利用一族测试函数,适用于具有更一般非梯度漂移的系统。数值结果在包括粗糙势和噪声数据设置在内的一系列高维稳态Fokker-Planck问题中,展示了准确且稳健的密度近似。
英文摘要
This paper develops a deep learning framework for solving high-dimensional stationary Fokker-Planck equations by combining Monte Carlo weak supervision, energy-variational physics constraints, and quasi-Newton refinement. Monte Carlo statistics anchor the scale of the stationary density, while a free-energy variational loss enforces equilibrium physics; the formulation also applies to stationary systems with pointwise orthogonal rotational components and, using a family of test functions, to systems with more general non-gradient drift. Numerical results demonstrate accurate and robust density approximations across a range of high-dimensional stationary Fokker-Planck problems, including rough-potential and noisy-data settings.