Abstract:Fourier Neural Operators are deep learning models that learn mappings between function spaces and can be used to learn and solve partial differential equations (PDEs), in some cases significantly faster than traditional PDE solvers. Within the model are Fourier layers, which apply linear transformations directly to the Fourier modes, with parameters depending on the wave numbers. However, most physical systems are isotropic, with the results being independent of the coordinate system chosen, but the linear transformations do not necessarily respect these symmetries. We propose a modification to the linear transformations that ensures spatial symmetries are respected, called the Isotropic Fourier Neural Operator, which both improves model performance and reduces the number of parameters by up to a factor of 16 in 2D and 96 in 3D.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.02597 [cs.LG] |
| (or arXiv:2605.02597v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02597 arXiv-issued DOI via DataCite (pending registration) |
From: Michael Staddon [view email]
[v1]
Mon, 4 May 2026 13:47:45 UTC (144 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。