Spectral neural operators
From MaRDI portal
Best approximation, Chebyshev systems (41A50) Asymptotic approximations, asymptotic expansions (steepest descent, etc.) (41A60) General integral transforms (44A05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Mesh generation, refinement, and adaptive methods for boundary value problems involving PDEs (65N50) Numerical methods for partial differential equations, boundary value problems (65N99) Numerical methods for discrete and fast Fourier transforms (65T50) Numerical methods for wavelets (65T60) Artificial neural networks and deep learning (68T07)
Abstract: A plentitude of applications in scientific computing requires the approximation of mappings between Banach spaces. Recently introduced Fourier Neural Operator (FNO) and Deep Operator Network (DeepONet) can provide this functionality. For both of these neural operators, the input function is sampled on a given grid (uniform for FNO), and the output function is parametrized by a neural network. We argue that this parametrization leads to 1) opaque output that is hard to analyze and 2) systematic bias caused by aliasing errors in the case of FNO. The alternative, advocated in this article, is to use Chebyshev and Fourier series for both domain and codomain. The resulting Spectral Neural Operator (SNO) has transparent output, never suffers from aliasing, and may include many exact (lossless) operations on functions. The functionality is based on well-developed fast, and stable algorithms from spectral methods. The implementation requires only standard numerical linear algebra. Our benchmarks show that for many operators, SNO is superior to FNO and DeepONet.
Recommendations
- Mitigating spectral bias for the multiscale operator learning with hierarchical attention
- Basis operator network: a neural network-based model for learning nonlinear operators via neural basis
- A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
- Neural and spectral operator surrogates: unified construction and expression rate bounds
- Residual-based error correction for neural operator accelerated Infinite-dimensional Bayesian inverse problems
Cites work
- A numerical and theoretical study of certain nonlinear wave phenomena
- Chebyshev and Fourier spectral methods.
- Comparing Numerical Methods for Ordinary Differential Equations
- Discretization-invariant Bayesian inversion and Besov space priors
- Learning data-driven discretizations for partial differential equations
- Spectral Methods in MATLAB
- The Korteweg-de Vries two-soliton solution as interacting two single solitons.
- Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems
Cited in
(27)- Residual-based error correction for neural operator accelerated Infinite-dimensional Bayesian inverse problems
- Mitigating spectral bias for the multiscale operator learning with hierarchical attention
- Basis operator network: a neural network-based model for learning nonlinear operators via neural basis
- Render unto numerics: orthogonal polynomial neural operator for PDEs with nonperiodic boundary conditions
- Physics-aware neural implicit solvers for multiscale, parametric PDEs with applications in heterogeneous media
- RandONets: shallow networks with random projections for learning linear and nonlinear operators
- Weak neural variational inference for solving Bayesian inverse problems \textit{without} forward models: applications in elastography
- Spectral informed neural networks
- Score-based diffusion models in function space
- XFNO: extended Fourier neural operator for solving parametric partial differential equations on general geometries
- Generalizability of local neural operator: example for elastodynamic problems
- Generating synthetic data for neural operators
- MCMC-Net: accelerating Markov chain Monte Carlo with neural networks for inverse problems
- U-shaped factorized Fourier neural operator for solving partial differential equations
- A hybrid iterative neural solver based on spectral analysis for parametric PDEs
- DGennO: a novel physics-aware neural operator for solving forward and inverse PDE problems based on deep, generative probabilistic modeling
- Accelerating space-time methods using physics-informed neural networks
- Are two hidden layers still enough for the physics-informed neural networks?
- AP-MIONet: asymptotic-preserving multiple-input neural operators for capturing the high-field limits of collisional kinetic equations
- Distribution free uncertainty quantification for neuroscience-inspired deep neural operators
- Finite element operator network for solving elliptic-type parametric PDEs
- About modifications of the loss function for the causal training of physics-informed neural networks
- A neural operator view on U-Nets for inverse imaging problems
- Improving data fidelity via diffusion model-based correction and super-resolution
- Enhancing Fourier neural operators with local spatial features
- Unsupervised operator learning approach for dissipative equations via Onsager principle
- HyperNOs: automated and parallel library for neural operators research
This page was built for publication: Spectral neural operators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6124382)
