Int-Deep: A Deep Learning Initialized Iterative Method for Nonlinear Problems

Abstract

This paper focuses on proposing a deep learning initialized iterative method (Int-Deep) for low-dimensional nonlinear partial differential equations (PDEs). The corresponding framework consists of two phases. In the first phase, an expectation minimization problem formulated from a given nonlinear PDE is approximately resolved with mesh-free deep neural networks to parametrize the solution space. In the second phase, a solution ansatz of the finite element method to solve the given PDE is obtained from the approximate solution in the first phase, and the ansatz can serve as a good initial guess such that Newton's method for solving the nonlinear PDE is able to converge to the ground truth solution with high-accuracy quickly. Systematic theoretical analysis is provided to justify the Int-Deep framework for several classes of problems. Numerical results show that the Int-Deep outperforms existing purely deep learning-based methods or traditional iterative methods (e.g., Newton's method and the Picard iteration method).

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Solving high-dimensional partial differential equations using deep learning
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Deep Network Approximation for Smooth Functions
• Optimal approximation of continuous functions by very deep ReLU networks
• Nonlinear Approximation via Compositions
• SelectNet: Self-paced Learning for High-dimensional Partial Differential Equations
• BCR-Net: a neural network based on the nonstandard wavelet form
• Study on a Poisson's Equation Solver Based On Deep Learning Technique
• Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem

Cited by in corpus (11)

• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• An augmented Lagrangian deep learning method for variational problems with essential boundary conditions
• Multi-scale Deep Neural Networks for Solving High Dimensional PDEs
• Structure Probing Neural Network Deflation
• Accelerating the convergence of Newton's method for nonlinear elliptic PDEs using Fourier neural operators
• Reproducing Activation Function for Deep Learning
• Asymptotic preserving scheme for anisotropic elliptic equations with deep neural network
• Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layers
• Universal Fourier Neural Operators for periodic homogenization problems in linear elasticity
• Adaptive Learning on the Grids for Elliptic Hemivariational Inequalities
• Convergent Graph Solvers