RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909382925615104 |
|---|---|
| author | Gattiglio, Guglielmo Grigoryeva, Lyudmila Tamborrino, Massimiliano |
| author_facet | Gattiglio, Guglielmo Grigoryeva, Lyudmila Tamborrino, Massimiliano |
| contents | Parallel-in-time (PinT) techniques have been proposed to solve systems of time-dependent differential equations by parallelizing the temporal domain. Among them, Parareal computes the solution sequentially using an inaccurate (fast) solver, and then "corrects" it using an accurate (slow) integrator that runs in parallel across temporal subintervals. This work introduces RandNet-Parareal, a novel method to learn the discrepancy between the coarse and fine solutions using random neural networks (RandNets). RandNet-Parareal achieves speed gains up to x125 and x22 compared to the fine solver run serially and Parareal, respectively. Beyond theoretical guarantees of RandNets as universal approximators, these models are quick to train, allowing the PinT solution of partial differential equations on a spatial mesh of up to $10^5$ points with minimal overhead, dramatically increasing the scalability of existing PinT approaches. RandNet-Parareal's numerical performance is illustrated on systems of real-world significance, such as the viscous Burgers' equation, the Diffusion-Reaction equation, the two- and three-dimensional Brusselator, and the shallow water equation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks Gattiglio, Guglielmo Grigoryeva, Lyudmila Tamborrino, Massimiliano Computation Distributed, Parallel, and Cluster Computing Numerical Analysis Machine Learning 68T07, 68T09, 65Y05, 65M55, 65M22, 65L05 Parallel-in-time (PinT) techniques have been proposed to solve systems of time-dependent differential equations by parallelizing the temporal domain. Among them, Parareal computes the solution sequentially using an inaccurate (fast) solver, and then "corrects" it using an accurate (slow) integrator that runs in parallel across temporal subintervals. This work introduces RandNet-Parareal, a novel method to learn the discrepancy between the coarse and fine solutions using random neural networks (RandNets). RandNet-Parareal achieves speed gains up to x125 and x22 compared to the fine solver run serially and Parareal, respectively. Beyond theoretical guarantees of RandNets as universal approximators, these models are quick to train, allowing the PinT solution of partial differential equations on a spatial mesh of up to $10^5$ points with minimal overhead, dramatically increasing the scalability of existing PinT approaches. RandNet-Parareal's numerical performance is illustrated on systems of real-world significance, such as the viscous Burgers' equation, the Diffusion-Reaction equation, the two- and three-dimensional Brusselator, and the shallow water equation. |
| title | RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks |
| topic | Computation Distributed, Parallel, and Cluster Computing Numerical Analysis Machine Learning 68T07, 68T09, 65Y05, 65M55, 65M22, 65L05 |
| url | https://arxiv.org/abs/2411.06225 |