Abstract:Matrix reordering in large sparse solvers seeks a permutation that minimizes factorization fill-in to reduce memory and computation. Because the minimum fill-in ordering problem is NP-complete and fill-in is implicit in the sparsity pattern, graph-theoretic heuristics are used. Existing reinforcement learning methods either ignore sparsity patterns--missing the global fill-in--or lack local exact fill-in feedback. We propose a graph policy optimization method, modeling fill-ins from global and local views: both the policy and value networks use a multi-hop graph neural backbone to embed global fill-in; the policy further interacts with symbolic factorization over graphs to extract local, step-level fill-ins, and the resulting feedback is aligned with the value network via an adaptive saturation function to improve convergence. On the SuiteSparse Matrix Collection, our method achieves mean reductions of 29.3 in fill-ins and 31.3 in peak memory usage over state-of-the-art baselines.
| Comments: | Accepted by ICASSP 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.17362 [cs.LG] |
| (or arXiv:2605.17362v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.17362 arXiv-issued DOI via DataCite (pending registration) |
From: Ziwei Li [view email]
[v1]
Sun, 17 May 2026 10:07:23 UTC (473 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。