arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09444cs.LGcs.NAmath.DSmath.NAstat.ML
收藏

扩展物理信息神经网络(XPINN)何时提高泛化能力?

When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?

National University of Singapore(新加坡国立大学);Brown University(布朗大学)

Zheyuan Hu, Ameya D. Jagtap, George Em Karniadakis, Kenji Kawaguchi

摘要:

物理信息神经网络(PINNs)由于其良好的逼近能力和泛化能力,已成为求解高维偏微分方程(PDE)的热门选择。近年来,基于区域分解方法的扩展PINNs(XPINNs)由于其在多尺度和多物理场问题建模及其并行化方面的有效性而引起了人们的广泛关注。然而,其收敛性和推广性质的理论认识仍然没有探索。在这项研究中,我们迈出了理解XPINN如何以及何时优于PINN的第一步。具体来说,对于一般的多层PINN和XPINN,我们首先通过PDE问题中目标函数的复杂性提供先验泛化界,并通过优化后网络的后验矩阵范数提供后验泛化界。此外,基于我们的边界,我们分析了XPINNs提高泛化能力的条件。具体地说,我们的理论表明,XPINN的关键组成部分,即区域分解,引入了一个权衡泛化。一方面,XPINN将复杂的PDE解决方案分解为几个简单的部分,这降低了学习每个部分所需的复杂性并提高了泛化能力。另一方面,分解导致在每个子域中可用的训练数据更少,并且因此这种模型通常倾向于过拟合并且可能变得不太可推广。从经验上讲,我们选择了五个偏微分方程来显示XPINN何时表现得比PINN更好,类似于PINN,或者比PINN更差,从而证明和证明我们的新理论。

英文摘要:

Physics-informed neural networks (PINNs) have become a popular choice for solving high-dimensional partial differential equations (PDEs) due to their excellent approximation power and generalization ability. Recently, Extended PINNs (XPINNs) based on domain decomposition methods have attracted considerable attention due to their effectiveness in modeling multiscale and multiphysics problems and their parallelization. However, theoretical understanding on their convergence and generalization properties remains unexplored. In this study, we take an initial step towards understanding how and when XPINNs outperform PINNs. Specifically, for general multi-layer PINNs and XPINNs, we first provide a prior generalization bound via the complexity of the target functions in the PDE problem, and a posterior generalization bound via the posterior matrix norms of the networks after optimization. Moreover, based on our bounds, we analyze the conditions under which XPINNs improve generalization. Concretely, our theory shows that the key building block of XPINN, namely the domain decomposition, introduces a tradeoff for generalization. On the one hand, XPINNs decompose the complex PDE solution into several simple parts, which decreases the complexity needed to learn each part and boosts generalization. On the other hand, decomposition leads to less training data being available in each subdomain, and hence such model is typically prone to overfitting and may become less generalizable. Empirically, we choose five PDEs to show when XPINNs perform better than, similar to, or worse than PINNs, hence demonstrating and justifying our new theory.

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。

↑