用于 Vlasov-福克aster 方程的深层动力学 JKO 方案
数值分析
2026-03-26 v1 数值分析
数学物理
math.MP
摘要
我们介绍一种基于深度神经网络的数值方法,用于求解动力学福克aster 方程,包括线性和非线性情况。在 Vlasov 类型方程的保守耗散结构基础上,我们构建了一类广义最小移动方案作为迭代约束最小化问题:保守部分决定约束集,而耗散部分定义目标函数。这导致了一种类似于经典 Jordan-Kinderlehrer-Otto (JKO) 方案的动力学 JKO 方案,即 Wasserstein 梯度流的 JKO 方案。为了计算动力学 JKO 迭代的每一步,我们引入了基于粒子的近似方法,其中速度场由深度神经网络参数化。 resulting algorithm can be interpreted as a kinetic-oriented neural differential equation that enables the representation of high-dimensional kinetic dynamics while preserving the essential variational and structural properties of the underlying PDE. We validate the method with extensive numerical experiments and demonstrate that the proposed kinetic JKO-neural ODE framework is effective for high-dimensional numerical simulations.
引用
@article{arxiv.2603.23901,
title = {Deep Kinetic JKO schemes for Vlasov-Fokker-Planck Equations},
author = {Wonjun Lee and Li Wang and Wuchen Li},
journal= {arXiv preprint arXiv:2603.23901},
year = {2026}
}
备注
28 pages