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 2406.00809math.NAcs.LGcs.NA
收藏

稀疏线性方程组迭代求解的图神经网络预条件子

Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems

MIT-IBM Watson AI Lab, IBM Research(MIT-IBM沃森人工智能实验室 IBM研究院)

Jie Chen

AI总结:

提出图神经网络预条件子(GNPs)用于大型稀疏线性方程组迭代求解,在超过800个矩阵上验证其构建时间更短且性能优于ILU、AMG等主流方法。

摘要:

预条件子在科学学科中大型稀疏线性方程组的迭代求解中处于核心地位。一些不访问矩阵本身以外信息的代数方法已被广泛研究和使用,但病态矩阵仍然非常具有挑战性。我们采用机器学习方法,提出使用图神经网络作为通用预条件子。它们在许多问题中展现出吸引人的性能,并且可以在主流预条件子表现不佳时使用。对超过800个矩阵的实证评估表明,这些图神经预条件子(GNPs)的构建时间更具可预测性,并且可以比其他广泛使用的预条件子(如ILU和AMG)短得多,同时执行时间比使用Krylov方法作为预条件子(如内-外GMRES中)更快。GNPs在解决不仅来自偏微分方程,还来自经济学、统计学、图和优化等大规模、具有挑战性的代数问题方面具有巨大潜力。

英文摘要:

Preconditioning is at the heart of iterative solutions of large, sparse linear systems of equations in scientific disciplines. Several algebraic approaches, which access no information beyond the matrix itself, are widely studied and used, but ill-conditioned matrices remain very challenging. We take a machine learning approach and propose using graph neural networks as a general-purpose preconditioner. They show attractive performance for many problems and can be used when the mainstream preconditioners perform poorly. Empirical evaluation on over 800 matrices suggests that the construction time of these graph neural preconditioners (GNPs) is more predictable and can be much shorter than that of other widely used ones, such as ILU and AMG, while the execution time is faster than using a Krylov method as the preconditioner, such as in inner-outer GMRES. GNPs have a strong potential for solving large-scale, challenging algebraic problems arising from not only partial differential equations, but also economics, statistics, graph, and optimization, to name a few.

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。

↑