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

Read full text Summarise with VIRAT
Authors: Benjamin Dörich, Roland Maier, Lukas Ullmer
Cited by: 0
References: 21

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Neural Networks and Applications Matrix Theory and Algorithms Model Reduction and Neural Networks

Publication details

Journal / source
arXiv (Cornell University)
Publication date
19 March 2026
Language
EN
Document type
Preprint