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 2311.00529math.NAcs.NA
收藏

物理信息神经网络误差分析的统一框架

A Unified Framework for the Error Analysis of Physics-Informed Neural Networks

Marius Zeinhofer, Rami Masri, Kent-André Mardal

AI总结:

该研究提出基于双线性形式的抽象框架,推导线性PDE下PINNs的先验与后验误差估计,分析多类PDE问题,揭示$L^2$惩罚对误差衰减的影响,并通过数值实验验证方法的精确求解能力。

摘要:

我们证明了用于求解线性偏微分方程(PDE)的物理信息神经网络(PINNs)的先验与后验误差估计。我们分析了原始形式和混合形式的椭圆方程、弹性方程、抛物方程、双曲方程、Stokes方程,以及一个PDE约束优化问题。为开展分析,我们提出了一个以双线性形式通用语言构建的抽象框架,并证明 coercivity(强制性)与连续性可推导出误差估计。所得估计是紧的,揭示了PINN公式中用于初始和边界条件的$L^2$惩罚方法会削弱误差衰减的范数。最后,利用PINN优化领域的最新进展,我们给出了数值算例,验证了该方法获得精确解的能力。

英文摘要:

We prove a priori and a posteriori error estimates for physics-informed neural networks (PINNs) for linear PDEs. We analyze elliptic equations in primal and mixed form, elasticity, parabolic, hyperbolic and Stokes equations; and a PDE constrained optimization problem. For the analysis, we propose an abstract framework in the common language of bilinear forms, and we show that coercivity and continuity lead to error estimates. The obtained estimates are sharp and reveal that the $L^2$ penalty approach for initial and boundary conditions in the PINN formulation weakens the norm of the error decay. Finally, utilizing recent advances in PINN optimization, we present numerical examples that illustrate the ability of the method to achieve accurate solutions.

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。

↑