Discretization Error of Fourier Neural Operators
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912605391552512 |
|---|---|
| author | Lanthaler, Samuel Stuart, Andrew M. Trautner, Margaret |
| author_facet | Lanthaler, Samuel Stuart, Andrew M. Trautner, Margaret |
| contents | Operator learning is a variant of machine learning that is designed to approximate maps between function spaces from data. The Fourier Neural Operator (FNO) is one of the main model architectures used for operator learning. The FNO combines linear and nonlinear operations in physical space with linear operations in Fourier space, leading to a parameterized map acting between function spaces. Although in definition, FNOs are objects in continuous space and perform convolutions on a continuum, their implementation is a discretized object performing computations on a grid, allowing efficient implementation via the FFT. Thus, there is a discretization error between the continuum FNO definition and the discretized object used in practice that is separate from other previously analyzed sources of model error. We examine this discretization error here and obtain algebraic rates of convergence in terms of the grid resolution as a function of the input regularity. Numerical experiments that validate the theory and describe model stability are performed. In addition, an algorithm is presented that leverages the discretization error and model error decomposition to optimize computational training time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02221 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discretization Error of Fourier Neural Operators Lanthaler, Samuel Stuart, Andrew M. Trautner, Margaret Numerical Analysis Machine Learning 41A35 (Primary) 65T50, 68T07 (Secondary) Operator learning is a variant of machine learning that is designed to approximate maps between function spaces from data. The Fourier Neural Operator (FNO) is one of the main model architectures used for operator learning. The FNO combines linear and nonlinear operations in physical space with linear operations in Fourier space, leading to a parameterized map acting between function spaces. Although in definition, FNOs are objects in continuous space and perform convolutions on a continuum, their implementation is a discretized object performing computations on a grid, allowing efficient implementation via the FFT. Thus, there is a discretization error between the continuum FNO definition and the discretized object used in practice that is separate from other previously analyzed sources of model error. We examine this discretization error here and obtain algebraic rates of convergence in terms of the grid resolution as a function of the input regularity. Numerical experiments that validate the theory and describe model stability are performed. In addition, an algorithm is presented that leverages the discretization error and model error decomposition to optimize computational training time. |
| title | Discretization Error of Fourier Neural Operators |
| topic | Numerical Analysis Machine Learning 41A35 (Primary) 65T50, 68T07 (Secondary) |
| url | https://arxiv.org/abs/2405.02221 |