A Greedy PDE Router for Blending Neural Operators and Classical Methods
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914535958380544 |
|---|---|
| author | Rayan, Sahana Patel, Yash Tewari, Ambuj |
| author_facet | Rayan, Sahana Patel, Yash Tewari, Ambuj |
| contents | When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency components. Designing an optimal hybrid iterative solver--where, at each iteration, a solver is selected from an ensemble of solvers to leverage their complementary strengths--poses a challenging combinatorial problem. While greedy selection is desirable for its constant-factor approximation guarantee to the optimal solution under Lipschitz assumptions, it requires knowledge of the true error at each step, which is unavailable in practice. We address this by proposing an approximate greedy router that efficiently mimics a greedy approach to solver selection. Empirical results on the Poisson and convection-diffusion equations show that our method consistently reduces final error and area-under-the-curve (AUC) of the error trajectory relative to single-solver baselines and existing hybrid approaches such as HINTS. In particular, our method reaches comparable error levels in substantially fewer iterations while exhibiting more stable error decay. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24814 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Greedy PDE Router for Blending Neural Operators and Classical Methods Rayan, Sahana Patel, Yash Tewari, Ambuj Methodology Machine Learning When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency components. Designing an optimal hybrid iterative solver--where, at each iteration, a solver is selected from an ensemble of solvers to leverage their complementary strengths--poses a challenging combinatorial problem. While greedy selection is desirable for its constant-factor approximation guarantee to the optimal solution under Lipschitz assumptions, it requires knowledge of the true error at each step, which is unavailable in practice. We address this by proposing an approximate greedy router that efficiently mimics a greedy approach to solver selection. Empirical results on the Poisson and convection-diffusion equations show that our method consistently reduces final error and area-under-the-curve (AUC) of the error trajectory relative to single-solver baselines and existing hybrid approaches such as HINTS. In particular, our method reaches comparable error levels in substantially fewer iterations while exhibiting more stable error decay. |
| title | A Greedy PDE Router for Blending Neural Operators and Classical Methods |
| topic | Methodology Machine Learning |
| url | https://arxiv.org/abs/2509.24814 |