Solving high-dimensional partial differential equations using deep learning
From MaRDI portal
Publication:4967451
Abstract: Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the "curse of dimensionality". This paper introduces a deep learning-based approach that can handle general high-dimensional parabolic PDEs. To this end, the PDEs are reformulated using backward stochastic differential equations and the gradient of the unknown solution is approximated by neural networks, very much in the spirit of deep reinforcement learning with the gradient acting as the policy function. Numerical results on examples including the nonlinear Black-Scholes equation, the Hamilton-Jacobi-Bellman equation, and the Allen-Cahn equation suggest that the proposed algorithm is quite effective in high dimensions, in terms of both accuracy and cost. This opens up new possibilities in economics, finance, operational research, and physics, by considering all participating agents, assets, resources, or particles together at the same time, instead of making ad hoc assumptions on their inter-relationships.
Recommendations
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus
- Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- DGM: a deep learning algorithm for solving partial differential equations
Cited in
(only showing first 100 items - show all)- Deep empirical risk minimization in finance: Looking into the future
- Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
- BCR-net: A neural network based on the nonstandard wavelet form
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Methods to recover unknown processes in partial differential equations using data
- Unbiased deep solvers for linear parametric PDEs
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
- Neural network-based variational methods for solving quadratic porous medium equations in high dimensions
- Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response
- Forward to the special topic on ``Solving differential equations with deep learning
- Number of solitons emerged in the initial profile of shallow water using convolutional neural networks
- A batch process for high dimensional imputation
- Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning
- Lookback option pricing under the double Heston model using a deep learning algorithm
- Committor functions via tensor networks
- Numerical algorithm with fifth-order accuracy for axisymmetric Laplace equation with linear boundary value problem
- On the locality of local neural operator in learning fluid dynamics
- Optimizing a portfolio of mean-reverting assets with transaction costs via a feedforward neural network
- Low-dimensional approximations of high-dimensional asset price models
- Approximation rates for neural networks with encodable weights in smoothness spaces
- Deep learning for constrained utility maximisation
- A deep learning method for solving high-order nonlinear soliton equations
- Nested Monte Carlo simulation in financial reporting: a review and a new hybrid approach
- Learning constitutive relations using symmetric positive definite neural networks
- Deep learning methods for partial differential equations and related parameter identification problems
- Solving parametric partial differential equations with deep rectified quadratic unit neural networks
- The backward Euler-Maruyama method for invariant measures of stochastic differential equations with super-linear coefficients
- A physics-informed learning approach to Bernoulli-type free boundary problems
- A numerical approach to Kolmogorov equation in high dimension based on Gaussian analysis
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Machine learning from a continuous viewpoint. I
- On a multilevel Levenberg-Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations
- A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations
- DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
- Discovering phase field models from image data with the pseudo-spectral physics informed neural networks
- A discontinuity capturing shallow neural network for elliptic interface problems
- Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- DEEP EQUILIBRIUM NETS
- Learning nonlocal constitutive models with neural networks
- Tensor decomposition methods for high-dimensional Hamilton-Jacobi-Bellman equations
- Scalable uncertainty quantification for deep operator networks using randomized priors
- Learning viscoelasticity models from indirect data using deep neural networks
- Deep Neural Networks for Solving Large Linear Systems Arising from High-Dimensional Problems
- Solving inverse stochastic problems from discrete particle observations using the Fokker-Planck equation and physics-informed neural networks
- Numerical solutions of boundary problems in partial differential equations: a deep learning framework with Green's function
- Solving Fokker-Planck equation using deep learning
- Adaptive deep density approximation for fractional Fokker-Planck equations
- Solving time dependent Fokker-Planck equations via temporal normalizing flow
- PFNN-2: a domain decomposed penalty-free neural network method for solving partial differential equations
- Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models
- Machine Learning Moment Closure Models for the Radiative Transfer Equation II: Enforcing Global Hyperbolicity in Gradient-Based Closures
- Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation
- Numerical solution and bifurcation analysis of nonlinear partial differential equations with extreme learning machines
- Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions
- Solving stochastic optimal control problem via stochastic maximum principle with deep learning method
- Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
- Machine learning for semi linear PDEs
- A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology
- Strong Solutions for PDE-Based Tomography by Unsupervised Learning
- Gauss Newton method for solving variational problems of PDEs with neural network discretizaitons
- A new deep neural network algorithm for multiple stopping with applications in options pricing
- On stability and regularization for data-driven solution of parabolic inverse source problems
- Asset pricing with general transaction costs: Theory and numerics
- Gabor-filtered Fourier neural operator for solving partial differential equations
- Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
- Neuro-PINN: a hybrid framework for efficient nonlinear projection equation solutions
- Deep learning of free boundary and Stefan problems
- MIM: a deep mixed residual method for solving high-order partial differential equations
- Structure preservation for the deep neural network multigrid solver
- Computing the invariant distribution of randomly perturbed dynamical systems using deep learning
- Physics informed by deep learning: numerical solutions of modified Korteweg-de Vries equation
- Approximate Optimal Controls via Instanton Expansion for Low Temperature Free Energy Computation
- Data-driven hedging of stock index options via deep learning
- Fractional Chebyshev deep neural network (FCDNN) for solving differential models
- DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress
- A Novel Deep Neural Network Algorithm for the Helmholtz Scattering Problem In the Unbounded Domain
- Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems
- \(r\)-adaptive deep learning method for solving partial differential equations
- Variable separated physics-informed neural networks based on adaptive weighted loss functions for blood flow model
- Error analysis of deep Ritz methods for elliptic equations
- Machine learning and computational mathematics
- Three ways to solve partial differential equations with neural networks — A review
- Partial differential equation regularization for supervised machine learning
- Lax-Oleinik-type formulas and efficient algorithms for certain high-dimensional optimal control problems
- Numerical simulation of Volterra-Fredholm integral equations using least squares support vector regression
- Probabilistic approach to mean field games and mean field type control problems with multiple populations
- A nonlocal physics-informed deep learning framework using the peridynamic differential operator
- A Deep Learning Method for Elliptic Hemivariational Inequalities
- The Calderón's problem via DeepONets
- Feynman-Kac equation for Brownian non-Gaussian polymer diffusion
- Non-diffusive neural network method for hyperbolic conservation laws
- Optimization of random feature method in the high-precision regime
- Temporal difference learning for high-dimensional PIDEs with jumps
- Numerical solution of a class of nonlinear partial differential equations by using barycentric interpolation collocation method
- An efficient weak Euler-Maruyama type approximation scheme of very high dimensional SDEs by orthogonal random variables
- A fully nonlinear Feynman-Kac formula with derivatives of arbitrary orders
This page was built for publication: Solving high-dimensional partial differential equations using deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4967451)
