Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities

Author:

Marcati Carlo,Opschoor Joost A. A.,Petersen Philipp C.,Schwab Christoph

Abstract

AbstractIn certain polytopal domains $$\varOmega $$ Ω , in space dimension $$d=2,3$$ d = 2 , 3 , we prove exponential expressivity with stable ReLU Neural Networks (ReLU NNs) in $$H^1(\varOmega )$$ H 1 ( Ω ) for weighted analytic function classes. These classes comprise in particular solution sets of source and eigenvalue problems for elliptic PDEs with analytic data. Functions in these classes are locally analytic on open subdomains $$D\subset \varOmega $$ D Ω , but may exhibit isolated point singularities in the interior of $$\varOmega $$ Ω or corner and edge singularities at the boundary $$\partial \varOmega $$ Ω . The exponential approximation rates are shown to hold in space dimension $$d = 2$$ d = 2 on Lipschitz polygons with straight sides, and in space dimension $$d=3$$ d = 3 on Fichera-type polyhedral domains with plane faces. The constructive proofs indicate that NN depth and size increase poly-logarithmically with respect to the target NN approximation accuracy $$\varepsilon >0$$ ε > 0 in $$H^1(\varOmega )$$ H 1 ( Ω ) . The results cover solution sets of linear, second-order elliptic PDEs with analytic data and certain nonlinear elliptic eigenvalue problems with analytic nonlinearities and singular, weighted analytic potentials as arise in electron structure models. Here, the functions correspond to electron densities that exhibit isolated point singularities at the nuclei.

Funder

Swiss Federal Institute of Technology Zurich

Publisher

Springer Science and Business Media LLC

Subject

Applied Mathematics,Computational Theory and Mathematics,Computational Mathematics,Analysis

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3