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

On Linear Convergence of ADMM for Decentralized Quantile Regression

Wang, Yue; Lian, Heng*
IEEE Transactions on Signal Processing2023DOI: 10.1109/TSP.2023.3325622
12阅读
引用收藏
分享

摘要

The alternating direction method of multipliers (ADMM) is a natural method of choice for distributed parameter learning. For smooth and strongly convex consensus optimization problems, it has been shown that ADMM and some of its variants enjoy linear convergence in the distributed setting, much like in the traditional non-distributed setting. The optimization problem associated with parameter estimation in quantile regression is neither smooth nor strongly convex (although is convex) and thus it seems can only have sublinear convergence at best. Although this insinuates slow convergence, we show that, if the local sample size is sufficiently large compared to parameter dimension and network size, distributed estimation in quantile regression actually exhibits linear convergence up to the statistical precision, the precise meaning of which will be explained in the text.

学科与关键词

关键词
ADMMlinear convergenceproximal operator
相关
加载中…
  • Communication-efficient estimation and inference for high-dimensional quantile regression based on smoothed decorrelated score
    Di, Fengrui; Wang, Lei*; Lian, HengStatistics in Medicine, 2022, 41(25): 5084-5101.被引 2
  • Convergence analysis of consensus-ADMM for general QCQP
    Huang, Huiping*; So, Hing Cheung; Zoubir, Abdelhak M.SIGNAL PROCESSING, 2023, 208: 108991.被引 2
  • Communication-efficient estimation of quantile matrix regression for massive datasets
    Yang, Yaohong; Wang, Lei; Liu, Jiamin; Li, Rui*; Lian, HengCOMPUTATIONAL STATISTICS & DATA ANALYSIS, 2023, 187: 107812.
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Signal Processing
发表日期
2023
卷期
第 71 卷
页码
3945-3955
DOI
10.1109/TSP.2023.3325622
语言
ENGLISH
成果收录
SCIE
资助标注
NSF Jiangxi Province [20223BCJ25017]; Hong Kong RGC general research [11300519, 11300721, 11311822]; CityU internal [7005514, 9680239]

作者

  • W

    Wang, Yue (第一作者)

  • L

    Lian, Heng (通讯)

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