An Augmented Lagrangian Deep Learning Method for Variational Problems with Essential Boundary Conditions
Year: 2022
Author: Jianguo Huang, Haoqin Wang, Tao Zhou
Communications in Computational Physics, Vol. 31 (2022), Iss. 3 : pp. 966–986
Abstract
This paper is concerned with a novel deep learning method for variational problems with essential boundary conditions. To this end, we first reformulate the original problem into a minimax problem corresponding to a feasible augmented Lagrangian, which can be solved by the augmented Lagrangian method in an infinite dimensional setting. Based on this, by expressing the primal and dual variables with two individual deep neural network functions, we present an augmented Lagrangian deep learning method for which the parameters are trained by the stochastic optimization method together with a projection technique. Compared to the traditional penalty method, the new method admits two main advantages: i) the choice of the penalty parameter is flexible and robust, and ii) the numerical solution is more accurate in the same magnitude of computational cost. As typical applications, we apply the new approach to solve elliptic problems and (nonlinear) eigenvalue problems with essential boundary conditions, and numerical experiments are presented to show the effectiveness of the new method.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/cicp.OA-2021-0176
Communications in Computational Physics, Vol. 31 (2022), Iss. 3 : pp. 966–986
Published online: 2022-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 21
Keywords: The augmented Lagrangian method deep learning variational problems saddle point problems essential boundary conditions.
Author Details
-
Render unto Numerics: Orthogonal Polynomial Neural Operator for PDEs with Nonperiodic Boundary Conditions
Liu, Ziyuan | Wang, Haifeng | Zhang, Hong | Bao, Kaijun | Qian, Xu | Song, SongheSIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 4 P.C323
https://doi.org/10.1137/23M1556320 [Citations: 0] -
A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations
Yuan, Lei | Ni, Yi-Qing | Deng, Xiang-Yun | Hao, ShuoJournal of Computational Physics, Vol. 462 (2022), Iss. P.111260
https://doi.org/10.1016/j.jcp.2022.111260 [Citations: 127] -
A Hybrid Iterative Method for Elliptic Variational Inequalities of the Second Kind
Cao, Yujian | Huang, Jianguo | Wang, HaoqinCommunications on Applied Mathematics and Computation, Vol. (2024), Iss.
https://doi.org/10.1007/s42967-024-00423-9 [Citations: 0] -
Monte Carlo fPINNs: Deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations
Guo, Ling | Wu, Hao | Yu, Xiaochen | Zhou, TaoComputer Methods in Applied Mechanics and Engineering, Vol. 400 (2022), Iss. P.115523
https://doi.org/10.1016/j.cma.2022.115523 [Citations: 31] -
Trans-Net: A transferable pretrained neural networks based on temporal domain decomposition for solving partial differential equations
Zhang, Dinglei | Li, Ying | Ying, ShihuiComputer Physics Communications, Vol. 299 (2024), Iss. P.109130
https://doi.org/10.1016/j.cpc.2024.109130 [Citations: 0] -
Feature Engineering with Regularity Structures
Chevyrev, Ilya | Gerasimovičs, Andris | Weber, HendrikJournal of Scientific Computing, Vol. 98 (2024), Iss. 1
https://doi.org/10.1007/s10915-023-02401-4 [Citations: 0] -
PINN-based approach to the consolidation analysis of visco-elastic soft soil around twin tunnels
Xie, Senlin | Hu, Anfeng | Xiao, Zhirong | Mariani, Stefano | Della Vecchia, GabrieleTunnelling and Underground Space Technology, Vol. 153 (2024), Iss. P.105981
https://doi.org/10.1016/j.tust.2024.105981 [Citations: 0] -
Domain Decomposition Learning Methods for Solving Elliptic Problems
Sun, Qi | Xu, Xuejun | Yi, HaotianSIAM Journal on Scientific Computing, Vol. 46 (2024), Iss. 4 P.A2445
https://doi.org/10.1137/22M1515392 [Citations: 0] -
IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning
Guo, Ling | Wu, Hao | Wang, Yan | Zhou, Wenwen | Zhou, TaoJournal of Computational Physics, Vol. 510 (2024), Iss. P.113089
https://doi.org/10.1016/j.jcp.2024.113089 [Citations: 0] -
Failure-Informed Adaptive Sampling for PINNs
Gao, Zhiwei | Yan, Liang | Zhou, TaoSIAM Journal on Scientific Computing, Vol. 45 (2023), Iss. 4 P.A1971
https://doi.org/10.1137/22M1527763 [Citations: 35]