ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Approximation of smooth functionals using deep ReLU networks

Song, Linhao*; Liu, Ying; Fan, Jun; Zhou, Ding-Xuan北京航空航天大学
Neural Networks2023-9DOI: 10.1016/j.neunet.2023.07.012
1被引16阅读
引用收藏
分享

摘要

In recent years, deep neural networks have been employed to approximate nonlinear continuous functionals F defined on L-p([-1, 1](s)) for 1 < p < 8. However, the existing theoretical analysis in the literature either is unsatisfactory due to the poor approximation results, or does not apply to the rectified linear unit (ReLU) activation function. This paper aims to investigate the approximation power of functional deep ReLU networks in two settings: F is continuous with restrictions on the modulus of continuity, and F has higher order Frechet derivatives. A novel functional network structure is proposed to extract features of higher order smoothness harbored by the target functional F. Quantitative rates of approximation in terms of the depth, width and total number of weights of neural networks are derived for both settings. We give logarithmic rates when measuring the approximation error on the unit ball of a Holder space. In addition, we establish nearly polynomial rates (i.e., rates of the form exp (-a(logM)(b)) with a > 0, 0 < b < 1) when measuring the approximation error on a space of analytic functions.

学科与关键词

关键词
Approximation theoryDeep learning theoryReLUSmooth functionalsFrechet derivativePolynomial rates
相关
加载中…
  • Approximation of Nonlinear Functionals Using Deep ReLU Networks
    Song, Linhao; Fan, Jun*; Chen, Di-Rong; Zhou, Ding-XuanJOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2023, 29(4): 50.被引 2
  • Approximation of Nonlinear Functionals Using Deep ReLU Networks (vol 29, 50, 2023)
    Song, Linhao; Fan, Jun*; Chen, Di-Rong; Zhou, Ding-XuanJOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2023, 29(5): 57.
  • Approximation of functions from Korobov spaces by deep convolutional neural networks
    Mao, Tong; Zhou, Ding-Xuan*ADVANCES IN COMPUTATIONAL MATHEMATICS, 2022, 48(6): 84.被引 2
查看全部 →

发表信息

论文状态
公开发表
期刊
Neural Networks
发表日期
2023-09
卷期
第 166 卷
页码
424-436
DOI
10.1016/j.neunet.2023.07.012
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [11971048]; Research Grants Council of Hong Kong [11307319, 11308121, 11318522, HKBU 12302819, HKBU 12301619, C1013-21GF]; Laboratory for AI-Powered Financial Technologies under the InnoHK initiative; Government of the HKSAR; Germany/Hong Kong Joint Research Scheme [G-CityU101/20]; CityU Strategic Interdisciplinary Research Grant [7020010]; National Science Foundation of China

作者

  • S

    Song, Linhao (通讯) (第一作者)

    beihang univ

  • L

    Liu, Ying

查看全部 4 位作者收起作者
  • F

    Fan, Jun

    hong kong baptist univ

  • Z

    Zhou, Ding-Xuan

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417