arXiv · 2611.12475
Learning to Select Sparse Linear Solvers with Convolutional Neural Networks
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Artemis Pados, Alan Edelman, Emmanuel Lujan, Daniel Pickard, Felipe Tome, Christopher Rackauckas. 2026-11-09. Learning to Select Sparse Linear Solvers with Convolutional Neural Networks. https://searcharxiv.com/abs/2611.12475
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.