Saved in:
Bibliographic Details
Main Authors: Versano, Idan, Turkel, Eli
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.13341
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917842462441472
author Versano, Idan
Turkel, Eli
author_facet Versano, Idan
Turkel, Eli
contents We present a novel architecture for learning geometry-aware preconditioners for linear partial differential equations (PDEs). We show that a deep operator network (Deeponet) can be trained on a simple geometry and remain a robust preconditioner for problems defined by different geometries without further fine-tuning or additional data mining. We demonstrate our method for the Helmholtz equation, which is used to solve problems in electromagnetics and acoustics; the Helmholtz equation is not positive definite, and with absorbing boundary conditions, it is not symmetric.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13341
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attention-based hybrid solvers for linear equations that are geometry aware
Versano, Idan
Turkel, Eli
Numerical Analysis
We present a novel architecture for learning geometry-aware preconditioners for linear partial differential equations (PDEs). We show that a deep operator network (Deeponet) can be trained on a simple geometry and remain a robust preconditioner for problems defined by different geometries without further fine-tuning or additional data mining. We demonstrate our method for the Helmholtz equation, which is used to solve problems in electromagnetics and acoustics; the Helmholtz equation is not positive definite, and with absorbing boundary conditions, it is not symmetric.
title Attention-based hybrid solvers for linear equations that are geometry aware
topic Numerical Analysis
url https://arxiv.org/abs/2411.13341