Deep Multigrid: learning prolongation and restriction matrices

Abstract

This paper proposes the method to optimize restriction and prolongation operators in the two-grid method. The proposed method is straightforwardly extended to the geometric multigrid method (GMM). GMM is used in solving discretized partial differential equation (PDE) and based on the restriction and prolongation operators. The operators are crucial for fast convergence of GMM, but they are unknown. To find them we propose a reformulation of the two-grid method in terms of a deep neural network with a specific architecture. This architecture is based on the idea that every operation in the two-grid method can be considered as a layer of a deep neural network. The parameters of layers correspond to the restriction and prolongation operators. Therefore, we state an optimization problem with respect to these operators and get optimal ones through backpropagation approach. To illustrate the performance of the proposed approach, we carry out experiments on the discretized Laplace equation, Helmholtz equation and singularly perturbed convection-diffusion equation and demonstrate that proposed approach gives operators, which lead to faster convergence.

References in corpus (1)

• Adam: A Method for Stochastic Optimization

Cited by in corpus (7)

• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• Variational training of neural network approximations of solution maps for physical models
• Deep Learning of Preconditioners for Conjugate Gradient Solvers in Urban Water Related Problems
• Learning optimal multigrid smoothers via neural networks
• Constrained Linear Data-feature Mapping for Image Classification
• Spectral substructured two-level domain decomposition methods
• How to optimize preconditioners for the conjugate gradient method: a stochastic approach