A Multiscale Neural Network Based on Hierarchical Matrices

DOI10.1137/18M1203602zbMath1435.65181arXiv1807.01883MaRDI QIDQ5222107

Lin Lin, Lexing Ying, Leonardo Zepeda-Núñez, Yu-Wei Fan

Publication date: 31 March 2020

Published in: Multiscale Modeling & Simulation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.01883

zbMATH Keywords

convolutional neural network\(\mathcal{H}\)-matrixlocally connected neural networkmultiscale neural network

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) PDEs in connection with biology, chemistry and other natural sciences (35Q92) NLS equations (nonlinear Schrödinger equations) (35Q55) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75) Computational density functional analysis in statistical mechanics (82M36)

Related Items (21)

Meta-learning pseudo-differential operators with deep neural networks ⋮ Int-Deep: a deep learning initialized iterative method for nonlinear problems ⋮ PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries ⋮ Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications ⋮ Using neural networks to accelerate the solution of the Boltzmann equation ⋮ MIM: a deep mixed residual method for solving high-order partial differential equations ⋮ AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems ⋮ MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs ⋮ Accuracy and architecture studies of residual neural network method for ordinary differential equations ⋮ Sparse Recovery of Elliptic Solvers from Matrix-Vector Products ⋮ Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics ⋮ A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks ⋮ Solving inverse problems with deep learning ⋮ Kernel methods are competitive for operator learning ⋮ Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data ⋮ Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks ⋮ Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning ⋮ A multiscale neural network based on hierarchical nested bases ⋮ SwitchNet: A Neural Network Model for Forward and Inverse Scattering Problems ⋮ Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data ⋮ Efficient long-range convolutions for point clouds

Uses Software

• Matlab
• TensorFlow
• DeepLab
• Keras
• ImageNet
• SegNet
• U-Net
• AlexNet
• DGM
• DnCNN

Cites Work

• Unnamed Item
• Fast construction of hierarchical matrix representation from matrix-vector multiplication
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Multiscale finite element methods for porous media flows and their applications
• A sparse matrix arithmetic based on \({\mathfrak H}\)-matrices. I: Introduction to \({\mathfrak H}\)-matrices
• Introduction to hierarchical matrices with applications.
• Hidden physics models: machine learning of nonlinear partial differential equations
• An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
• A sparse \({\mathcal H}\)-matrix arithmetic: General complexity estimates
• DGM: a deep learning algorithm for solving partial differential equations
• Deep multiscale model learning
• Deep relaxation: partial differential equations for optimizing deep neural networks
• A multiscale neural network based on hierarchical nested bases
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Convergence analysis of the Generalized Empirical Interpolation Method
• Efficient reduced-basis treatment of nonaffine and nonlinear partial differential equations
• Multi-Level Adaptive Solutions to Boundary-Value Problems
• Spectral Methods in MATLAB
• Literature survey on low rank approximation of matrices
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Computing the Ground State Solution of Bose--Einstein Condensates by a Normalized Gradient Flow
• An introduction to hierarchical matrices
• Solving high-dimensional partial differential equations using deep learning
• Solving parametric PDE problems with artificial neural networks
• Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
• Generalized Multiscale Finite Element Methods. Nonlinear Elliptic Equations
• A fast algorithm for particle simulations

This page was built for publication: A Multiscale Neural Network Based on Hierarchical Matrices