Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Enrui, Kahana, Adar, Kopaničáková, Alena, Turkel, Eli, Ranade, Rishikesh, Pathak, Jay, Karniadakis, George Em
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913487295348736
author Zhang, Enrui
Kahana, Adar
Kopaničáková, Alena
Turkel, Eli
Ranade, Rishikesh
Pathak, Jay
Karniadakis, George Em
author_facet Zhang, Enrui
Kahana, Adar
Kopaničáková, Alena
Turkel, Eli
Ranade, Rishikesh
Pathak, Jay
Karniadakis, George Em
contents Neural networks suffer from spectral bias having difficulty in representing the high frequency components of a function while relaxation methods can resolve high frequencies efficiently but stall at moderate to low frequencies. We exploit the weaknesses of the two approaches by combining them synergistically to develop a fast numerical solver of partial differential equations (PDEs) at scale. Specifically, we propose HINTS, a hybrid, iterative, numerical, and transferable solver by integrating a Deep Operator Network (DeepONet) with standard relaxation methods, leading to parallel efficiency and algorithmic scalability for a wide class of PDEs, not tractable with existing monolithic solvers. HINTS balances the convergence behavior across the spectrum of eigenmodes by utilizing the spectral bias of DeepONet, resulting in a uniform convergence rate and hence exceptional performance of the hybrid solver overall. Moreover, HINTS applies to large-scale, multidimensional systems, it is flexible with regards to discretizations, computational domain, and boundary conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2208_13273
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
Zhang, Enrui
Kahana, Adar
Kopaničáková, Alena
Turkel, Eli
Ranade, Rishikesh
Pathak, Jay
Karniadakis, George Em
Numerical Analysis
Machine Learning
Neural networks suffer from spectral bias having difficulty in representing the high frequency components of a function while relaxation methods can resolve high frequencies efficiently but stall at moderate to low frequencies. We exploit the weaknesses of the two approaches by combining them synergistically to develop a fast numerical solver of partial differential equations (PDEs) at scale. Specifically, we propose HINTS, a hybrid, iterative, numerical, and transferable solver by integrating a Deep Operator Network (DeepONet) with standard relaxation methods, leading to parallel efficiency and algorithmic scalability for a wide class of PDEs, not tractable with existing monolithic solvers. HINTS balances the convergence behavior across the spectrum of eigenmodes by utilizing the spectral bias of DeepONet, resulting in a uniform convergence rate and hence exceptional performance of the hybrid solver overall. Moreover, HINTS applies to large-scale, multidimensional systems, it is flexible with regards to discretizations, computational domain, and boundary conditions.
title Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2208.13273