Numerical Analysis on Neural Network Projected Schemes for Approximating One Dimensional Wasserstein Gradient Flows
CoRR(2024)
摘要
We provide a numerical analysis and computation of neural network projected
schemes for approximating one dimensional Wasserstein gradient flows. We
approximate the Lagrangian mapping functions of gradient flows by the class of
two-layer neural network functions with ReLU (rectified linear unit) activation
functions. The numerical scheme is based on a projected gradient method, namely
the Wasserstein natural gradient, where the projection is constructed from the
L^2 mapping spaces onto the neural network parameterized mapping space. We
establish theoretical guarantees for the performance of the neural projected
dynamics. We derive a closed-form update for the scheme with well-posedness and
explicit consistency guarantee for a particular choice of network structure.
General truncation error analysis is also established on the basis of the
projective nature of the dynamics. Numerical examples, including gradient drift
Fokker-Planck equations, porous medium equations, and Keller-Segel models,
verify the accuracy and effectiveness of the proposed neural projected
algorithm.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要