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 2603.19043math.NAcs.NA
收藏

神经网络求解结构线性方程组的复杂度界限

Complexity bounds on neural networks for the solution of structured linear systems of equations

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Benjamin Dörich, Roland Maier, Lukas Ullmer

AI总结:

本文研究了ReLU神经网络求解对称正定稀疏矩阵线性方程组的复杂度上限,结合改良Richardson和共轭梯度法特性,提出与矩阵规模和条件数相关的显式层数和神经元数量界限。

摘要:

我们推导了ReLU神经网络近似求解线性方程组的复杂度上限,重点研究对称正定稀疏矩阵,扩展了矩阵求逆结果至线性方程求解,利用改良Richardson和共轭梯度法的有利性质,所提出的层数和神经元数量界限不仅与矩阵规模相关,也与条件数相关。

英文摘要:

We derive upper bounds on the complexity of ReLU neural networks approximating the solution of a linear system given the matrix and the right-hand side. We focus on matrices which are symmetric positive definite and sparse, as they appear in the context of finite difference and finite element methods. For such matrices, we extend available results for the matrix inversion to the task of solving a linear system, where we leverage favorable properties of classical methods such as the modified Richardson and the conjugate gradient method. Our bounds on the number of layers and neurons are not only explicit with respect to the size of the matrices, but also with respect to their condition numbers.

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。

↑