DGM: a deep learning algorithm for solving partial differential equations

DOI10.1016/j.jcp.2018.08.029zbMath1416.65394arXiv1708.07469OpenAlexW2749028154MaRDI QIDQ2002333

Justin A. Sirignano, Konstantinos V. Spiliopoulos

Publication date: 11 July 2019

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1708.07469

zbMATH Keywords

partial differential equationsmachine learningdeep learninghigh-dimensional partial differential equations

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs (65M12) Quasilinear parabolic equations (35K59) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Related Items (only showing first 100 items - show all)

Probabilistic partition of unity networks for high‐dimensional regression problems ⋮ DEEP EQUILIBRIUM NETS ⋮ A convolutional dispersion relation preserving scheme for the acoustic wave equation ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Physics-Informed Neural Networks for Solving Dynamic Two-Phase Interface Problems ⋮ VC-PINN: variable coefficient physics-informed neural network for forward and inverse problems of PDEs with variable coefficient ⋮ A Neural Network Approach to High-Dimensional Optimal Switching Problems with Jumps in Energy Markets ⋮ Deep learning methods for partial differential equations and related parameter identification problems ⋮ Artificial neural networks for solving elliptic differential equations with boundary layer ⋮ Numerical solution of the modified and non-Newtonian Burgers equations by stochastic coded trees ⋮ Some elliptic second order problems and neural network solutions: existence and error estimates ⋮ A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems ⋮ MG-CNN: a deep CNN to predict saddle points of matrix games ⋮ Deep neural network solution for finite state mean field game with error estimation ⋮ On the recovery of internal source for an elliptic system by neural network approximation ⋮ Neural networks for first order HJB equations and application to front propagation with obstacle terms ⋮ Adaptive deep density approximation for fractional Fokker-Planck equations ⋮ The deep minimizing movement scheme ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ The Random Feature Method for Time-Dependent Problems ⋮ A deep learning method for solving third-order nonlinear evolution equations ⋮ CD-ROM: complemented deep -- reduced order model ⋮ BINN: a deep learning approach for computational mechanics problems based on boundary integral equations ⋮ Computing non-equilibrium trajectories by a deep learning approach ⋮ A dimension-augmented physics-informed neural network (DaPINN) with high level accuracy and efficiency ⋮ Fully probabilistic deep models for forward and inverse problems in parametric PDEs ⋮ Solving Elliptic Problems with Singular Sources Using Singularity Splitting Deep Ritz Method ⋮ Deep Ritz method with adaptive quadrature for linear elasticity ⋮ On the use of neural networks for full waveform inversion ⋮ Deep learning for thermal plasma simulation: solving 1-D arc model as an example ⋮ Exponential ReLU neural network approximation rates for point and edge singularities ⋮ Accuracy and architecture studies of residual neural network method for ordinary differential equations ⋮ A class of mesh-free algorithms for some problems arising in finance and machine learning ⋮ DeepBHCP: deep neural network algorithm for solving backward heat conduction problems ⋮ FDM-PINN: Physics-informed neural network based on fictitious domain method ⋮ Radial basis function neural network (RBFNN) approximation of Cauchy inverse problems of the Laplace equation ⋮ Data-driven vortex solitons and parameter discovery of 2D generalized nonlinear Schrödinger equations with a \(\mathcal{PT}\)-symmetric optical lattice ⋮ The robust physics-informed neural networks for a typical fourth-order phase field model ⋮ Physics-informed deep learning for melting heat transfer analysis with model-based transfer learning ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ Learning Optimal Multigrid Smoothers via Neural Networks ⋮ Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning ⋮ Error estimates and physics informed augmentation of neural networks for thermally coupled incompressible Navier Stokes equations ⋮ Deep learning discrete calculus (DLDC): a family of discrete numerical methods by universal approximation for STEM education to frontier research ⋮ A Chebyshev Polynomial Neural Network Solver for Boundary Value Problems of Elliptic Equations ⋮ A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations ⋮ Solving an inverse source problem by deep neural network method with convergence and error analysis ⋮ Investigating and Mitigating Failure Modes in Physics-Informed Neural Networks (PINNs) ⋮ The Kolmogorov infinite dimensional equation in a Hilbert space via deep learning methods ⋮ Accelerated Share Repurchases Under Stochastic Volatility ⋮ Higher-order error estimates for physics-informed neural networks approximating the primitive equations ⋮ A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations ⋮ Neural Galerkin schemes with active learning for high-dimensional evolution equations ⋮ A mathematical perspective of machine learning ⋮ Capturing the diffusive behavior of the multiscale linear transport equations by asymptotic-preserving convolutional deeponets ⋮ Addressing discontinuous root-finding for subsequent differentiability in machine learning, inverse problems, and control ⋮ Pseudo-Hamiltonian neural networks for learning partial differential equations ⋮ Physics informed WNO ⋮ An extreme learning machine-based method for computational PDEs in higher dimensions ⋮ Transferable neural networks for partial differential equations ⋮ A conservative hybrid deep learning method for Maxwell-Ampère-Nernst-Planck equations ⋮ Deep learning-based schemes for singularly perturbed convection-diffusion problems ⋮ Number of solitons emerged in the initial profile of shallow water using convolutional neural networks ⋮ A new method for solving nonlinear partial differential equations based on liquid time-constant networks ⋮ Variational inference in neural functional prior using normalizing flows: application to differential equation and operator learning problems ⋮ A Rate of Convergence of Weak Adversarial Neural Networks for the Second Order Parabolic PDEs ⋮ A Novel Deep Neural Network Algorithm for the Helmholtz Scattering Problem In the Unbounded Domain ⋮ Neural Networks with Local Converging Inputs (NNLCI) for Solving Conservation Laws, Part II: 2D Problems ⋮ A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology ⋮ Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons ⋮ \(r\)-adaptive deep learning method for solving partial differential equations ⋮ Error analysis of deep Ritz methods for elliptic equations ⋮ Label-free learning of elliptic partial differential equation solvers with generalizability across boundary value problems ⋮ Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs ⋮ Convergence Analysis of a Quasi-Monte CarloBased Deep Learning Algorithm for Solving Partial Differential Equations ⋮ MC-Nonlocal-PINNs: Handling Nonlocal Operators in PINNs Via Monte Carlo Sampling ⋮ HRW: Hybrid Residual and Weak Form Loss for Solving Elliptic Interface Problems with Neural Network ⋮ Less is more: a new machine-learning methodology for spatiotemporal systems ⋮ Physics-informed variational inference for uncertainty quantification of stochastic differential equations ⋮ Numerical methods for backward stochastic differential equations: a survey ⋮ Efficient pricing and hedging of high-dimensional American options using deep recurrent networks ⋮ Meshless methods for American option pricing through physics-informed neural networks ⋮ Asymptotic-preserving neural networks for multiscale time-dependent linear transport equations ⋮ Numerical computation of partial differential equations by hidden-layer concatenated extreme learning machine ⋮ Deep Curve-Dependent PDEs for Affine Rough Volatility ⋮ A Mesh-Free Algorithm to Solve an Inverse Source Problem for Degenerate Two-Dimensional Parabolic Equation from Final Observations ⋮ Analytical derivatives of neural networks ⋮ Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs ⋮ Convolution hierarchical deep-learning neural network (C-HiDeNN) with graphics processing unit (GPU) acceleration ⋮ Improved training of physics-informed neural networks for parabolic differential equations with sharply perturbed initial conditions ⋮ A symmetry group based supervised learning method for solving partial differential equations ⋮ Exact Dirichlet boundary physics-informed neural network EPINN for solid mechanics ⋮ Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations ⋮ A Deep Energy Method for the Analysis of Thermoporoelastic Functionally Graded Beams ⋮ Adaptive Learning Rate Residual Network Based on Physics-Informed for Solving Partial Differential Equations ⋮ A Scalable Deep Learning Approach for Solving High-Dimensional Dynamic Optimal Transport ⋮ Failure-Informed Adaptive Sampling for PINNs ⋮ Least-squares neural network (LSNN) method for scalar nonlinear hyperbolic conservation laws: discrete divergence operator ⋮ An artificial neural network approach to identify the parameter in a nonlinear subdiffusion model ⋮ Unnamed Item

Uses Software

• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Option pricing with a direct adaptive sparse grid approach
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Numerical solution for high order differential equations using a hybrid neural network-optimization method
• Compact sets in the space \(L^ p(0,T;B)\)
• Lattice approximations for stochastic quasi-linear parabolic partial differential equations driven by space-time white noise. I
• Nonlinear parabolic equations with measure data
• Existence of solutions for some ``noncoercive parabolic equations
• Existence results for a Cauchy-Dirichlet parabolic problem with a repulsive gradient term
• HJB equations in infinite dimensions under weak regularizing properties
• Neural algorithm for solving differential equations
• Stochastic simulation: Algorithms and analysis
• Stationary Hamilton--Jacobi Equations in Hilbert Spaces and Applications to a Stochastic Optimal Control Problem
• EXISTENCE RESULT FOR NONLINEAR PARABOLIC EQUATIONS WITH LOWER ORDER TERMS
• Optimal control of a stochastic heat equation with boundary-noise and boundary-control
• Pricing American Options: A Duality Approach
• Gradient Convergence in Gradient methods with Errors
• Convergence of numerical schemes for the solution of parabolic stochastic partial differential equations
• Monte Carlo valuation of American options
• A highly parallel Black–Scholes solver based on adaptive sparse grids
• Analysis of linear difference schemes in the sparse grid combination technique
• Sparse grids
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Efficient Hierarchical Approximation of High‐Dimensional Option Pricing Problems
• Approximation by superpositions of a sigmoidal function

This page was built for publication: DGM: a deep learning algorithm for solving partial differential equations