A theoretical analysis of deep neural networks and parametric PDEs
From MaRDI portal
Publication:2117329
DOI10.1007/S00365-021-09551-4OpenAlexW3167031531WikidataQ114229767 ScholiaQ114229767MaRDI QIDQ2117329FDOQ2117329
Authors: Gitta Kutyniok, Philipp Petersen, Mones Raslan, Reinhold Schneider 
Publication date: 21 March 2022
Published in: Constructive Approximation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1904.00377
Recommendations
- Numerical solution of the parametric diffusion equation by deep neural networks
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- Error analysis for deep neural network approximations of parametric hyperbolic conservation laws
- Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
- Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
Learning and adaptive systems in artificial intelligence (68T05) Numerical analysis (65-XX) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Theoretical approximation in context of PDEs (35A35) Rate of convergence, degree of approximation (41A25) Elliptic equations and elliptic systems (35J99) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)
Cites Work
- Reduced basis methods for partial differential equations. An introduction
- DGM: a deep learning algorithm for solving partial differential equations
- Universal approximation bounds for superpositions of a sigmoidal function
- On the mathematical foundations of learning
- Deep learning
- Gaussian elimination is not optimal
- Multilayer feedforward networks are universal approximators
- Convergence rates for greedy algorithms in reduced basis methods
- Efficient reduced-basis treatment of nonaffine and nonlinear partial differential equations
- Approximation by superpositions of a sigmoidal function
- Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations. Application to transport and continuum mechanics.
- Lower bounds for approximation by MLP neural networks
- Greedy algorithms for reduced bases in Banach spaces
- How to best sample a solution manifold?
- Certified reduced basis methods for parametrized partial differential equations
- Approximation of high-dimensional parametric PDEs
- Breaking the curse of dimensionality in sparse polynomial approximation of parametric PDEs
- Recent advances in reduction methods for nonlinear problems
- On making large nonlinear problems small
- Numerical solution of the parametric diffusion equation by deep neural networks
- Solving parametric PDE problems with artificial neural networks
- Sparse polynomial approximation of parametric elliptic PDEs. Part I: affine coefficients
- A posteriori error analysis of the reduced basis method for nonaffine parametrized nonlinear PDEs
- Multilevel approximation of parametric and stochastic PDES
- Reduced basis method for quadratically nonlinear transport equations
- Kolmogorov widths and low-rank approximations of parametric elliptic PDEs
- Approximation properties of a multilayered feedforward artificial neural network
- Fully discrete approximation of parametric and stochastic elliptic PDEs
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Solving high-dimensional partial differential equations using deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Introduction to uncertainty quantification
- Non-intrusive reduced order modeling of nonlinear problems using neural networks
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Error bounds for approximations with deep ReLU networks
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Deep hidden physics models: deep learning of nonlinear partial differential equations
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- Optimal approximation with sparsely connected deep neural networks
- Data driven approximation of parametrized PDEs by reduced basis and neural networks
- Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
- Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
- Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- Parametric PDEs: sparse or low-rank approximations?
- Provable approximation properties for deep neural networks
- Deep ReLU networks and high-order finite element methods
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
- ReLU deep neural networks and linear finite elements
- Equivalence of approximation by convolutional neural networks and fully-connected networks
- Deep Neural Network Approximation Theory
Cited In (62)
- Deep learning methods for partial differential equations and related parameter identification problems
- A Theoretical Analysis of Deep Neural Networks and Parametric PDEs
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations
- Two-Layer Neural Networks with Values in a Banach Space
- Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
- Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs
- Sparse polynomial approximations for affine parametric saddle point problems
- A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
- Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting)
- Reduced basis methods for time-dependent problems
- An overview on deep learning-based approximation methods for partial differential equations
- Mesh-informed neural networks for operator learning in finite element spaces
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- A machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problems
- A neural network multigrid solver for the Navier-Stokes equations
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis
- Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
- Approximation properties of residual neural networks for Kolmogorov PDEs
- Linear/ridge expansions: enhancing linear approximations by ridge functions
- Deep Surrogate Accelerated Delayed-Acceptance Hamiltonian Monte Carlo for Bayesian Inference of Spatio-Temporal Heat Fluxes in Rotating Disc Systems
- Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
- A New Certified Hierarchical and Adaptive RB-ML-ROM Surrogate Model for Parametrized PDEs
- An introduction to the mathematics of deep learning
- DNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equations
- wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws
- The mathematics of artificial intelligence
- A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
- Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE
- Neural Network Approximation of Coarse-Scale Surrogates in Numerical Homogenization
- Title not available (Why is that?)
- PDE-aware deep learning for inverse problems in cardiac electrophysiology
- Connections between numerical algorithms for PDEs and neural networks
- Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs
- Space-time error estimates for deep neural network approximations for differential equations
- Solving traveltime tomography with deep learning
- Approximations with deep neural networks in Sobolev time-space
- Learning high frequency data via the coupled frequency predictor-corrector triangular DNN
- Designing rotationally invariant neural networks from PDEs and variational methods
- Discretization of parameter identification in PDEs using neural networks
- Greedy training algorithms for neural networks and applications to PDEs
- Variational physics informed neural networks: the role of quadratures and test functions
- Limitations of neural network training due to numerical instability of backpropagation
- An artificial neural network approach to bifurcating phenomena in computational fluid dynamics
- DeepBND: a machine learning approach to enhance multiscale solid mechanics
- Unbiased deep solvers for linear parametric PDEs
- Deep convolutional Ritz method: parametric PDE surrogates without labeled data
- Full error analysis for the training of deep neural networks
- Long-time prediction of nonlinear parametrized dynamical systems by deep learning-based reduced order models
- Operator learning using random features: a tool for scientific computing
- Error analysis for deep neural network approximations of parametric hyperbolic conservation laws
- One-shot learning of surrogates in PDE-constrained optimization under uncertainty
- Inf-sup neural networks for high-dimensional elliptic PDE problems
- Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
- Approximation rates for deep calibration of (rough) stochastic volatility models
- Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
- Statistical variational data assimilation
- The deep arbitrary polynomial chaos neural network or how deep artificial neural networks could benefit from data-driven homogeneous chaos theory
- Approximation results for gradient flow trained shallow neural networks in \(1d\)
- Learning quantities of interest from parametric PDEs: an efficient neural-weighted minimal residual approach
- Neural network expression rates and applications of the deep parametric PDE method in counterparty credit risk
Uses Software
This page was built for publication: A theoretical analysis of deep neural networks and parametric PDEs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117329)
