A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
From MaRDI portal
(Redirected from Publication:2216499)
curse of dimensionalitydeep neural networkshigh-dimensional PDEsinformation based complexitymultilevel Picard approximations
Probabilistic methods, stochastic differential equations (65C99) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75) Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07)
Abstract: Deep neural networks and other deep learning methods have very successfully been applied to the numerical approximation of high-dimensional nonlinear parabolic partial differential equations (PDEs), which are widely used in finance, engineering, and natural sciences. In particular, simulations indicate that algorithms based on deep learning overcome the curse of dimensionality in the numerical approximation of solutions of semilinear PDEs. For certain linear PDEs this has also been proved mathematically. The key contribution of this article is to rigorously prove this for the first time for a class of nonlinear PDEs. More precisely, we prove in the case of semilinear heat equations with gradient-independent nonlinearities that the numbers of parameters of the employed deep neural networks grow at most polynomially in both the PDE dimension and the reciprocal of the prescribed approximation accuracy. Our proof relies on recently introduced multilevel Picard approximations of semilinear PDEs.
Recommendations
- 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
- Uniform error estimates for artificial neural network approximations for heat 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
- Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
- Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
Cites work
- Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep optimal stopping
- DGM: a deep learning algorithm for solving partial differential equations
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- On multilevel Picard numerical approximations for high-dimensional nonlinear parabolic partial differential equations and high-dimensional nonlinear backward stochastic differential equations
- Solving high-dimensional partial differential equations using deep learning
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
Cited in
(97)- Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations
- Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
- Spectral methods for nonlinear functionals and functional differential equations
- Computing Lyapunov functions using deep neural networks
- Numerical solution of the parametric diffusion equation by deep 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
- Multilevel Picard iterations for solving smooth semilinear parabolic heat equations
- Data-driven soliton solutions and model parameters of nonlinear wave models via the conservation-law constrained neural network method
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- A theoretical analysis of deep neural networks and parametric PDEs
- SelectNet: self-paced learning for high-dimensional partial differential equations
- MIM: a deep mixed residual method for solving high-order partial differential equations
- Extensions of the deep Galerkin method
- DeepSets and their derivative networks for solving symmetric PDEs
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- The deep parametric PDE method and applications to option pricing
- Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
- Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks
- Convergence of the deep BSDE method for coupled FBSDEs
- Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
- Neural networks in Fréchet spaces
- Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
- Space-time error estimates for deep neural network approximations for differential equations
- Approximation properties of residual neural networks for Kolmogorov PDEs
- An overview on deep learning-based approximation methods for partial differential equations
- Deep splitting method for parabolic PDEs
- Deep backward schemes for high-dimensional nonlinear PDEs
- Tensor decomposition methods for high-dimensional Hamilton-Jacobi-Bellman equations
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- 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
- Approximations with deep neural networks in Sobolev time-space
- Full error analysis for the training of deep neural networks
- Uniform error estimates for artificial neural network approximations for heat equations
- Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions
- Unbiased deep solvers for linear parametric PDEs
- Deep neural network surrogates for nonsmooth quantities of interest in shape uncertainty quantification
- Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
- Deep network approximation characterized by number of neurons
- Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
- Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations
- Stationary Density Estimation of Itô Diffusions Using Deep Learning
- Convergence of a Robust Deep FBSDE Method for Stochastic Control
- A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
- Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
- DEEP EQUILIBRIUM NETS
- Three ways to solve partial differential equations with neural networks — A review
- Deep learning methods for partial differential equations and related parameter identification problems
- Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation
- Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning
- The Kolmogorov infinite dimensional equation in a Hilbert space via deep learning methods
- An extreme learning machine-based method for computational PDEs in higher dimensions
- Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
- Numerical methods for backward stochastic differential equations: a survey
- Adaptive Learning Rate Residual Network Based on Physics-Informed for Solving Partial Differential Equations
- Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus
- Approximation properties of residual neural networks for fractional differential equations
- Mobility Estimation for Langevin Dynamics Using Control Variates
- Pricing options on flow forwards by neural networks in a Hilbert space
- The use of physics-informed neural network approach to image restoration via nonlinear PDE tools
- Neural Control of Parametric Solutions for High-Dimensional Evolution PDEs
- Designing universal causal deep learning models: The geometric (Hyper)transformer
- Deep learning algorithms for solving high-dimensional nonlinear backward stochastic differential equations
- Solving PDEs on unknown manifolds with machine learning
- Deep neural network expressivity for optimal stopping problems
- The Calderón's problem via DeepONets
- Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces
- Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
- Rectified deep neural networks overcome the curse of dimensionality when approximating solutions of McKean-Vlasov stochastic differential equations
- Recent developments in machine learning methods for stochastic control and games
- Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations
- Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations
- Random neural networks for rough volatility
- Generalization error analysis of deep backward dynamic programming for solving nonlinear PDEs
- Bounds on the approximation error for deep neural networks applied to dispersive models: nonlinear waves
- Adaptive neural network basis methods for partial differential equations with low-regular solutions
- Multilevel Picard approximations overcome the curse of dimensionality when approximating semilinear heat equations with gradient-dependent nonlinearities in L^p-sense
- A Global-in-Time Neural Network Approach to Dynamic Portfolio Optimization
- Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations
- Enhancing dynamic CT image reconstruction with neural fields and optical flow
- Interpolating between BSDEs and PINNs: deep learning for elliptic and parabolic boundary value problems
- Multilevel Picard approximations overcome the curse of dimensionality in the numerical approximation of general semilinear PDEs with gradient-dependent nonlinearities
- Towards continuous mathematical models for the analysis of classes of deep neural networks
- The neural network basis method for nonlinear partial differential equations and its Gauss-Newton optimizer
- Full error analysis of the random deep splitting method for nonlinear parabolic PDEs and PIDEs
- Residual multi-fidelity neural network computing
- Approximation of solution operators for high-dimensional PDEs
- A deep solver for backward stochastic Volterra integral equations
- Multilevel Picard algorithm for general semilinear parabolic PDEs with gradient-dependent nonlinearities
- Walk-on-Spheres Monte Carlo and deep neural network approximations of elliptic PDEs with drift and killing
- Neural networks in non-metric spaces
- Numerical analysis of residual neural networks for stochastic partial differential equations
- Finite Expression Approximation of High-Dimensional PDEs Without the Curse of Dimensionality
- Convergence of kernel and neural-network methods for Hamilton--Jacobi--Bellman equations on unbounded domains
- Energetic Variational Deep Learning for Solving High-Dimensional Stationary Fokker-Planck Equations
- Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures
- Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
This page was built for publication: A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2216499)
