跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.12475 · v1

Learning to Select Sparse Linear Solvers with Convolutional Neural Networks

首次提交 2026-11-09 22:22
版本更新 2026-11-09 22:22
雷达观测 2026-11-10 15:22
arXiv ↗PDF ↗

摘要

We investigate convolutional-neural-network (CNN) based automatic solver selection for sparse linear systems, a problem of practical importance where solver performance varies dramatically with matrix sparsity structure. A CNN is trained to regress log timing ratios between candidate solvers using spy plot images of matrix nonzero structure as input, achieving strong prediction accuracy on both held-out SuiteSparse matrices and real-world matrices from high-performance simulation codes.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-09 22:22 · 最新观测版本

Learning to Select Sparse Linear Solvers with Convolutional Neural Networks

We investigate convolutional-neural-network (CNN) based automatic solver selection for sparse linear systems, a problem of practical importance where solver performance varies dramatically with matrix sparsity structure. A CNN is trained to regress log timing ratios between candidate solvers using spy plot images of matrix nonzero structure as input, achieving strong prediction accuracy on both held-out SuiteSparse matrices and real-world matrices from high-performance simulation codes.

查看此版本解读 →查看此版本原文 ↗