A Multi-Scale DNN Algorithm for Nonlinear Elliptic Equations with Multiple Scales

DOI10.4208/cicp.OA-2020-0187zbMath1474.65445arXiv2009.14597OpenAlexW3100666994MaRDI QIDQ5162363

Xian Li, Lei Zhang, Zhi-Qin John Xu

Publication date: 2 November 2021

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

Full work available at URL: https://arxiv.org/abs/2009.14597

zbMATH Keywords

variational formulation\(p\)-Laplacian equationactivation functiondeep neural network (DNN)multi-scale elliptic problem

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Nonlinear boundary value problems for nonlinear elliptic equations (35J66)

Related Items (11)

Solving multiscale elliptic problems by sparse radial basis function neural networks ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs ⋮ Learning Specialized Activation Functions for Physics-Informed Neural Networks ⋮ A novel multi-scale loss function for classification problems in machine learning ⋮ Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs ⋮ Adaptive Learning Rate Residual Network Based on Physics-Informed for Solving Partial Differential Equations ⋮ A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks ⋮ Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions ⋮ Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions ⋮ A deep domain decomposition method based on Fourier features

Uses Software

• DGM
• MscaleDNN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Numerical homogenization of the acoustic wave equations with a continuum of scales
• Machine learning from a continuous viewpoint. I
• The general theory of homogenization. A personalized introduction
• A multiscale model reduction method for nonlinear monotone elliptic equations in heterogeneous media
• The element-free Galerkin method for the nonlinear \(p\)-Laplacian equation
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• DGM: a deep learning algorithm for solving partial differential equations
• Finite difference methods for the infinity Laplace and \(p\)-Laplace equations
• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
• Data driven governing equations approximation using deep neural networks
• A mesh-free method for interface problems using the deep learning approach
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Error bounds for approximations with deep ReLU networks
• Preconditioned descent algorithms for \(p\)-Laplacian
• A Hybridizable Discontinuous Galerkin Method for the $p$-Laplacian
• Analysis of the finite element heterogeneous multiscale method for quasilinear elliptic homogenization problems
• Polyharmonic homogenization, rough polyharmonic splines and sparse super-localization
• Optimality of an adaptive finite element method for the p-Laplacian equation
• Fractional estimates for non-differentiable elliptic systems with general growth
• Multiscale Finite Element Methods
• Homogenization of Parabolic Equations with a Continuum of Space and Time Scales
• Finite Element Approximation of the Parabolic p-Laplacian
• Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields using Convolutional Neural Networks
• Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
• WEB-Spline-based mesh-free finite element approximation forp-Laplacian

This page was built for publication: A Multi-Scale DNN Algorithm for Nonlinear Elliptic Equations with Multiple Scales