arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14566math.NAcs.NA
收藏

深度反向动态规划求解非线性偏微分方程的泛化误差分析

Generalization Error Analysis of Deep Backward Dynamic Programming for Solving Nonlinear PDEs

Du Ouyang, Jichang Xiao, Xiaoqun Wang

AI总结:

本研究分析深度反向动态规划求解非线性偏微分方程的泛化误差,证明拟蒙特卡洛方法比蒙特卡洛方法具有更高收敛阶,数值实验验证其更精确稳定。

摘要:

我们探索了拟蒙特卡洛(QMC)方法在深度反向动态规划(DBDP)(Hure等人,2020年)中的应用,用于数值求解高维非线性偏微分方程(PDEs)。我们的研究聚焦于检验泛化误差作为DBDP框架中总误差的一个组成部分,发现泛化误差的收敛速率受采样方法选择的影响。具体而言,对于给定的批量大小$m$,QMC方法下的泛化误差展现出$O(m^{-1+\varepsilon})$的收敛速率,其中$\varepsilon$可以任意小。这一速率显著优于传统蒙特卡洛(MC)方法的$O(m^{-1/2+\varepsilon})$。我们的理论分析表明,QMC方法下的泛化误差实现了比MC方法更高阶的收敛。数值实验证明,QMC在提供更精确且稳定的解方面确实优于MC。

英文摘要:

We explore the application of the quasi-Monte Carlo (QMC) method in deep backward dynamic programming (DBDP) (Hure et al. 2020) for numerically solving high-dimensional nonlinear partial differential equations (PDEs). Our study focuses on examining the generalization error as a component of the total error in the DBDP framework, discovering that the rate of convergence for the generalization error is influenced by the choice of sampling methods. Specifically, for a given batch size $m$, the generalization error under QMC methods exhibits a convergence rate of $O(m^{-1+\varepsilon})$, where $\varepsilon$ can be made arbitrarily small. This rate is notably more favorable than that of the traditional Monte Carlo (MC) methods, which is $O(m^{-1/2+\varepsilon})$. Our theoretical analysis shows that the generalization error under QMC methods achieves a higher order of convergence than their MC counterparts. Numerical experiments demonstrate that QMC indeed surpasses MC in delivering solutions that are both more precise and stable.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑