Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations

DOI10.1016/J.JCP.2022.110996OpenAlexW4226429807WikidataQ114163364 ScholiaQ114163364MaRDI QIDQ2133752FDOQ2133752

Yuyan Chen, Jinchao Xu, Bin Dong

Publication date: 5 May 2022

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

Full work available at URL: https://arxiv.org/abs/2010.14088

zbMATH Keywords

meta-learningmultigriddeep-learningmgnetparameterized PDEs

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for partial differential equations, boundary value problems (65Nxx) Basic methods in fluid mechanics (76Mxx)

Cites Work

• MgNet: a unified framework of multigrid and convolutional neural network
• DGM: a deep learning algorithm for solving partial differential equations
• Iterative Methods by Space Decomposition and Subspace Correction
• The method of alternating projections and the method of subspace corrections in Hilbert space
• A survey of projection-based model reduction methods for parametric dynamical systems
• Analysis and convergence of the MAC scheme. II. Navier-Stokes equations
• Title not available (Why is that?)
• Reduced-order modeling of parameterized PDEs using time-space-parameter principal component analysis
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Sharp Estimates for Multigrid Rates of Convergence with General Smoothing and Acceleration
• Solving high-dimensional partial differential equations using deep learning
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Algebraic multigrid methods
• Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks
• Stable architectures for deep neural networks
• A proposal on machine learning via dynamical systems
• MetaInv-Net
• Convergence analysis of triangular MAC schemes for two dimensional Stokes equations
• Detecting troubled-cells on two-dimensional unstructured grids using a neural network
• A mesh-free method for interface problems using the deep learning approach
• DLGA-PDE: discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
• Multi-Scale Deep Neural Network (MscaleDNN) for Solving Poisson-Boltzmann Equation in Complex Domains
• Analysis of a two-level method for anisotropic diffusion equations on aligned and nonaligned grids

Cited In (10)

• MgNet: a unified framework of multigrid and convolutional neural network
• Meta-auto-decoder: a meta-learning-based reduced order model for solving parametric partial differential equations
• AI‐enhanced iterative solvers for accelerating the solution of large‐scale parametrized systems
• Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Differential Equations
• Learning-based local weighted least squares for algebraic multigrid method
• Multigrid-augmented deep learning preconditioners for the Helmholtz equation using compact implicit layers
• Generative downscaling of PDE solvers with physics-guided diffusion models
• Side effects of learning from low-dimensional data embedded in a Euclidean space
• An enhanced V-cycle MgNet model for operator learning in numerical partial differential equations
• Fourier neural operator based fluid-structure interaction for predicting the vesicle dynamics

Uses Software

• torchdiffeq
• MgNet
• DGM
• MetaInv-Net
• MscaleDNN

   Recommendations

• A metalearning approach for physics-informed neural networks (PINNs): application to parameterized PDEs 👍 👎
• MgNet: a unified framework of multigrid and convolutional neural network 👍 👎
• Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation 👍 👎
• DGM: a deep learning algorithm for solving partial differential equations 👍 👎
• Meta-learning pseudo-differential operators with deep neural networks 👍 👎
• A neural network multigrid solver for the Navier-Stokes equations 👍 👎
• Isogeometric neural networks: a new deep learning approach for solving parameterized partial differential equations 👍 👎
• Structure preservation for the deep neural network multigrid solver 👍 👎
• Diffusion maps-aided neural networks for the solution of parametrized PDEs 👍 👎

This page was built for publication: Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2133752)