arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.14151math.NAcs.NA
收藏

高阶椭圆方程深度混合残差方法的误差分析

Error Analysis of the Deep Mixed Residual Method for High-order Elliptic Equations

Mengjia Bai, Jingrun Chen, Rui Du, Zhiwei Sun

AI总结:

本文对求解高阶椭圆方程的深度混合残差方法进行先验误差分析,通过有界性与强制性分析及 Céa 引理分解误差,并利用 Barron 空间理论证明其可避免维度灾难且降低激活函数正则性要求。

摘要:

本文对用于求解具有非齐次边界条件(包括 Dirichlet、Neumann 和 Robin 条件)的高阶椭圆方程的深度混合残差方法(MIM)进行了先验误差分析。我们考察了具有两类损失函数的 MIM,分别称为一阶和二阶最小二乘系统。通过给出有界性和强制性分析,我们利用 Céa 引理将总误差分解为逼近误差、泛化误差和优化误差。利用 Barron 空间理论和 Rademacher 复杂度,推导出关于训练样本和网络规模的先验误差,该误差不受维度灾难的影响。我们的结果表明,与深度 Ritz 方法相比,MIM 显著降低了对激活函数的正则性要求,这表明 MIM 在求解高阶方程方面具有有效性。

英文摘要:

This paper presents an a priori error analysis of the Deep Mixed Residual method (MIM) for solving high-order elliptic equations with non-homogeneous boundary conditions, including Dirichlet, Neumann, and Robin conditions. We examine MIM with two types of loss functions, referred to as first-order and second-order least squares systems. By providing boundedness and coercivity analysis, we leverage Céa's Lemma to decompose the total error into the approximation, generalization, and optimization errors. Utilizing the Barron space theory and Rademacher complexity, an a priori error is derived regarding the training samples and network size that are exempt from the curse of dimensionality. Our results reveal that MIM significantly reduces the regularity requirements for activation functions compared to the deep Ritz method, implying the effectiveness of MIM in solving high-order equations.

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。

↑