Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver
From MaRDI portal
Spectral, collocation and related methods for initial value and initial-boundary value problems involving PDEs (65M70) Multigrid methods; domain decomposition for boundary value problems involving PDEs (65N55) Complexity and performance of numerical algorithms (65Y20) Artificial neural networks and deep learning (68T07)
Cites work
- A Benchmark for the Bayesian Inversion of Coefficients in Partial Differential Equations
- A calculation procedure for heat, mass and momentum transfer in three- dimensional parabolic flows
- A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
- A hybrid iterative method based on MIONet for PDEs: Theory and numerical examples
- A New Convergence Proof for the Multigrid Method Including the V-Cycle
- A proposal on machine learning via dynamical systems
- A Structured Matrix Method for Nonequispaced Neural Operators
- Accurate, high-order representation of complex three-dimensional surfaces via Fourier continuation analysis
- Active operator learning with predictive uncertainty quantification for partial differential equations
- Adaptive operator learning for infinite-dimensional Bayesian inverse problems
- An operator learning perspective on parameter-to-observable maps
- Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
- Bayesian calibration of computer models. (With discussion)
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
- Calibrate, emulate, sample
- Can a finite element method perform arbitrarily badly?
- Choose a Transformer: Fourier or Galerkin
- Continuum attention for neural operators
- Convergence Rates for Learning Linear Operators from Noisy Data
- Data Assimilation in Reduced Modeling
- Data-driven balancing of linear dynamical systems
- Data-driven operator inference for nonintrusive projection-based model reduction
- Deep operator network approximation rates for Lipschitz operators
- DeepGreen: Deep Learning of Green's Functions for Nonlinear Boundary Value Problems
- DeepOMamba: state-space model for spatio-temporal PDE neural operator learning
- DeepXDE: a deep learning library for solving differential equations
- DUE: a deep learning framework and library for modeling unknown equations
- Dynamic mode decomposition of numerical and experimental data
- Easy Uncertainty Quantification (EasyUQ): Generating Predictive Distributions from Single-Valued Model Output
- Efficient PDE-Constrained optimization under high-dimensional uncertainty using derivative-informed neural operators
- Enforcing Dirichlet Boundary Conditions in Operator Learning
- Exponential time differencing for stiff systems
- Fourier Neural Operator for Parametric Partial Differential Equations
- Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
- Geometric Generalization of Neural Operators from Kernel Integral Perspective
- Gevrey class regularity for the solutions of the Navier-Stokes equations
- Hamiltonian systems and transformations in Hilbert space.
- Iterative Methods by Space Decomposition and Subspace Correction
- KalmanNet: neural network aided Kalman filtering for partially known dynamics
- Learning elliptic partial differential equations with randomized linear algebra
- Learning Neural Operators on Riemannian Manifolds
- Machine Learning in Aerodynamic Shape Optimization
- Model reduction and neural networks for parametric PDEs
- Multigrid methods
- Multiscale Neural Networks for Approximating Green's Functions
- Multiwavelet-based Operator Learning for Differential Equations
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- NeuralUQ: A Comprehensive Library for Uncertainty Quantification in Neural Differential Equations and Operators
- Non-intrusive reduced order modeling of nonlinear problems using neural networks
- Nonlocality and nonlinearity implies universality in operator learning
- On universal approximation and error bounds for Fourier Neural Operators
- Optimizing the optimizer for physics-informed neural networks and Kolmogorov-Arnold networks
- Point Cloud Neural Operator for Parametric PDEs on Complex and Variable Geometries
- Residual-based error correction for neural operator accelerated Infinite-dimensional Bayesian inverse problems
- Solving and Learning Nonlinear PDEs with Gaussian Processes
- Spectral analysis of nonlinear flows
- Spectral properties of dynamical systems, model reduction and decompositions
- SPFNO: Spectral operator learning for PDEs with Dirichlet and Neumann boundary conditions
- Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
- Stable architectures for deep neural networks
- Survey of multifidelity methods in uncertainty propagation, inference, and optimization
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
- Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
- The cost-accuracy trade-off in operator learning with neural networks
- The GNAT method for nonlinear model reduction: Effective implementation and application to computational fluid dynamics and turbulent flows
- The method of alternating projections and the method of subspace corrections in Hilbert space
- The Random Feature Model for Input-Output Maps between Banach Spaces
- Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
This page was built for publication: Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7353442)
