A Rate of Convergence of Weak Adversarial Neural Networks for the Second Order Parabolic PDEs

IF 2.6 3区 物理与天体物理 Q1 PHYSICS, MATHEMATICAL Communications in Computational Physics Pub Date : 2023-06-01 DOI:10.4208/cicp.oa-2023-0063
Yuling Jiao, Jerry Zhijian Yang, Cheng Yuan null, Junyu Zhou
{"title":"A Rate of Convergence of Weak Adversarial Neural Networks for the Second Order Parabolic PDEs","authors":"Yuling Jiao, Jerry Zhijian Yang, Cheng Yuan null, Junyu Zhou","doi":"10.4208/cicp.oa-2023-0063","DOIUrl":null,"url":null,"abstract":". In this paper, we give the first rigorous error estimation of the Weak Ad-versarial Neural Networks (WAN) in solving the second order parabolic PDEs. By decomposing the error into approximation error and statistical error, we first show the weak solution can be approximated by the ReLU 2 with arbitrary accuracy, then prove that the statistical error can also be efficiently bounded by the Rademacher complexity of the network functions, which can be further bounded by some integral related with the covering numbers and pseudo-dimension of ReLU 2 space. Finally, by combining the two bounds, we prove that the error of the WAN method can be well controlled if the depth and width of the neural network as well as the sample numbers have been properly selected. Our result also reveals some kind of freedom in choosing sample numbers on ∂ Ω and in the time axis.","PeriodicalId":50661,"journal":{"name":"Communications in Computational Physics","volume":"12 1","pages":"0"},"PeriodicalIF":2.6000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Communications in Computational Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4208/cicp.oa-2023-0063","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, MATHEMATICAL","Score":null,"Total":0}
引用次数: 0

Abstract

. In this paper, we give the first rigorous error estimation of the Weak Ad-versarial Neural Networks (WAN) in solving the second order parabolic PDEs. By decomposing the error into approximation error and statistical error, we first show the weak solution can be approximated by the ReLU 2 with arbitrary accuracy, then prove that the statistical error can also be efficiently bounded by the Rademacher complexity of the network functions, which can be further bounded by some integral related with the covering numbers and pseudo-dimension of ReLU 2 space. Finally, by combining the two bounds, we prove that the error of the WAN method can be well controlled if the depth and width of the neural network as well as the sample numbers have been properly selected. Our result also reveals some kind of freedom in choosing sample numbers on ∂ Ω and in the time axis.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
二阶抛物型偏微分方程弱对抗神经网络的收敛速度
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Communications in Computational Physics
Communications in Computational Physics 物理-物理:数学物理
CiteScore
4.70
自引率
5.40%
发文量
84
审稿时长
9 months
期刊介绍: Communications in Computational Physics (CiCP) publishes original research and survey papers of high scientific value in computational modeling of physical problems. Results in multi-physics and multi-scale innovative computational methods and modeling in all physical sciences will be featured.
期刊最新文献
A Model-Data Asymptotic-Preserving Neural Network Method Based on Micro-Macro Decomposition for Gray Radiative Transfer Equations A Causality-DeepONet for Causal Responses of Linear Dynamical Systems JefiPIC: A 3-D Full Electromagnetic Particle-in-Cell Simulator Based on Jefimenko’s Equations on GPU A Comparative Study of Hydrodynamic Lattice Boltzmann Equation in Phase-Field-Based Multiphase Flow Models Finite-Volume TENO Scheme with a New Cell-Interface Flux Evaluation Strategy for Unstructured Meshes
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1