arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.25017math.NAcs.LGcs.NAq-fin.CPstat.ML
收藏

深度梯度流方法求解偏微分方程的泛化误差收敛性

Convergence of the generalization error for deep gradient flow methods for PDEs

Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands.;Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands \& Institute of Applied;Delft Institute of Applied Mathematics, EEMCS, TU Delft, 2628 Delft, The Netherlands

Chenguang Liu, Antonis Papapantoleon, Jasper Rou

AI总结:

本文研究深度梯度流方法求解高维偏微分方程的泛化误差收敛性,通过分解误差并分析极限条件,证明在神经元数量和训练时间趋于无穷大时,泛化误差趋于零。

摘要:

本文旨在为深度梯度流方法(DGFMs)求解(高维)偏微分方程(PDEs)提供坚实的数学基础。我们将DGFMs的泛化误差分解为近似误差和训练误差。首先,我们证明满足合理且可验证假设的PDE解可以被神经网络近似,因此随着神经元数量趋于无穷大,近似误差趋于零。接着,我们推导了在“宽网络极限”下训练过程所遵循的梯度流,并分析了训练时间趋于无穷大时该流的极限。这些结果结合表明,随着神经元数量和训练时间趋于无穷大,DGFMs的泛化误差趋于零。

英文摘要:

The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization error of DGFMs into an approximation and a training error. We first show that the solution of PDEs that satisfy reasonable and verifiable assumptions can be approximated by neural networks, thus the approximation error tends to zero as the number of neurons tends to infinity. Then, we derive the gradient flow that the training process follows in the ``wide network limit'' and analyze the limit of this flow as the training time tends to infinity. These results combined show that the generalization error of DGFMs tends to zero as the number of neurons and the training time tend to infinity.

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。

↑