arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.06017math.NAcs.NA
收藏

神经网络近似的后验分析

A posteriori analysis of neural network approximations of partial differential equations

Monash University(莫纳什大学)

Thomas Führer, Sergio Rojas

AI总结:

针对解与近似解的误差衡量问题,在一般变分公式适定条件下,证明误差等价于两个可计算或可估计的残差之和,可用于神经网络输出误差估计,优化中能监测误差或纳入损失函数控制误差。

摘要:

在一般情况下,我们研究有限元分析中用于衡量解与其近似之间误差的后验估计,其中近似不一定由有限元方法生成。我们证明,若基础变分公式适定,则误差等价于两个残差之和。第一项是残差到有限维空间的投影,因此可计算;第二项在许多实际场景中可通过可计算的上界可靠估计。假设足够精确的求积,我们的发现可用于估计例如神经网络输出的误差。优化过程中可考虑两个重要应用:一是用估计器监测每个求解器步骤的误差,二是将两个估计器纳入损失函数以控制误差。我们还考虑了二阶椭圆偏微分方程作为模型问题,讨论其不同变分公式及边界条件纳入估计器的多种选项,并通过数值实验验证了发现。

英文摘要:

With the aim of defining robust losses for the neural network approximation of partial differential equations, we study, in a general setting, a posteriori estimates used in finite element analysis. We show that the error is equivalent to the sum of two residuals provided that the underlying variational formulation is well-posed. The first contribution is the projection of the residual to a finite-dimensional space and is therefore computable, while the second one can be reliably estimated by a computable upper bound in many practical scenarios. Two important applications can be considered during the neural network optimization (training) process: first, the computable lower bound is used as loss functional and both contributions are used to monitor the error at each solver step; or second, the two estimators are included in the loss functional, thereby providing total control over the error. As a model problem, we consider a second-order elliptic partial differential equation and discuss several variational formulations, including different approaches for incorporating boundary conditions into the estimators. Various numerical experiments are presented to validate our findings.

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。

↑