Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.03833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909690296795136 |
|---|---|
| author | Kim, Sungyoon Dwaraknath, Rajat Vadiraj geng, Longling Pilanci, Mert |
| author_facet | Kim, Sungyoon Dwaraknath, Rajat Vadiraj geng, Longling Pilanci, Mert |
| contents | Iterative methods for computing matrix functions have been extensively studied and their convergence speed can be significantly improved with the right tuning of parameters and by mixing different iteration types. Handtuning the design options for optimal performance can be cumbersome, especially in modern computing environments: numerous different classical iterations and their variants exist, each with non-trivial per-step cost and tuning parameters. To this end, we propose MatRL -- a reinforcement learning based framework that automatically discovers iterative algorithms for computing matrix functions. The key idea is to treat algorithm design as a sequential decision-making process. Monte-Carlo tree search is then used to plan a hybrid sequence of matrix iterations and step sizes, tailored to a specific input matrix distribution and computing environment. Moreover, we also show that the learned algorithms provably generalize to sufficiently large matrices drawn from the same distribution. Finally, we corroborate our theoretical results with numerical experiments demonstrating that MatRL produces algorithms that outperform various baselines in the literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search Kim, Sungyoon Dwaraknath, Rajat Vadiraj geng, Longling Pilanci, Mert Machine Learning Iterative methods for computing matrix functions have been extensively studied and their convergence speed can be significantly improved with the right tuning of parameters and by mixing different iteration types. Handtuning the design options for optimal performance can be cumbersome, especially in modern computing environments: numerous different classical iterations and their variants exist, each with non-trivial per-step cost and tuning parameters. To this end, we propose MatRL -- a reinforcement learning based framework that automatically discovers iterative algorithms for computing matrix functions. The key idea is to treat algorithm design as a sequential decision-making process. Monte-Carlo tree search is then used to plan a hybrid sequence of matrix iterations and step sizes, tailored to a specific input matrix distribution and computing environment. Moreover, we also show that the learned algorithms provably generalize to sufficiently large matrices drawn from the same distribution. Finally, we corroborate our theoretical results with numerical experiments demonstrating that MatRL produces algorithms that outperform various baselines in the literature. |
| title | MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.03833 |