Convergence Rate of Distributed Subgradient Methods under Communication Delays

被引：0
|
作者：
Doan, Thinh T. [1 ]
Beck, Carolyn L. [1 ]
Srikant, R. [1 ]
机构：
[1] Univ Illinois, Coordinated Sci Lab, Urbana, IL 61801 USA
来源：
2018 ANNUAL AMERICAN CONTROL CONFERENCE (ACC) | 2018年
基金：
美国国家科学基金会;
关键词：
OPTIMIZATION; CONSENSUS;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Motivated by broad applications in computer science and engineering, we study distributed algorithms for optimization problems over a network of nodes, where the goal is to optimize a global objective composed of a sum of local functions. In this paper, we consider a popular distributed gradient-based consensus algorithm, which only requires local computation and communication. A significant problem in this area is to analyze the convergence rate of such algorithms in the presence of communication delays that are inevitable in distributed systems. Our main contribution is to obtain an upper bound on the rate of convergence of the algorithm as a function of the network size, topology, and the inter-node communication delays.
引用
收藏
页码：5310 / 5315
页数：6
相关论文
共 50 条
  • [1] On the Convergence of Distributed Subgradient Methods under Quantization
    Doan, Thinh T.
    Maguluri, Siva Theja
    Romberg, Justin
    [J]. 2018 56TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2018, : 567 - 574
  • [2] On the Convergence Rate of Distributed Gradient Methods for Finite-Sum Optimization under Communication Delays
    Doan T.T.
    Beck C.L.
    Srikant R.
    [J]. Performance Evaluation Review, 2018, 46 (01): : 93 - 95
  • [3] On the convergence rate of distributed gradient methods for finite-sum optimization under communication delays
    [J]. 1600, Association for Computing Machinery (01):
  • [4] On the rate of convergence of distributed asynchronous subgradient methods for multi-agent optimization
    Nedic, Angelia
    Ozdaglar, Asuman
    [J]. PROCEEDINGS OF THE 46TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-14, 2007, : 4197 - +
  • [5] Asynchronous Subgradient Methods with Unbounded Delays for Communication Networks
    Gatsis, Nikolaos
    Giannakis, Georgios B.
    [J]. 2012 IEEE 51ST ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2012, : 5870 - 5875
  • [6] Convergence rate analysis of distributed optimization with projected subgradient algorithm
    Liu, Shuai
    Qiu, Zhirong
    Xie, Lihua
    [J]. AUTOMATICA, 2017, 83 : 162 - 169
  • [7] Convergence Analysis of Distributed Subgradient Methods over Random Networks
    Lobel, Ilan
    Ozdaglar, Asuman
    [J]. 2008 46TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING, VOLS 1-3, 2008, : 353 - +
  • [8] Distributed Subgradient Method for Multi-Agent Optimization with Communication Delays
    Liu Jun
    Li Dequan
    Yin Zhixiang
    [J]. 2013 32ND CHINESE CONTROL CONFERENCE (CCC), 2013, : 6762 - 6767
  • [9] Fast Convergence Rates of Distributed Subgradient Methods With Adaptive Quantization
    Doan, Thinh T.
    Maguluri, Siva Theja
    Romberg, Justin
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2021, 66 (05) : 2191 - 2205
  • [10] Convergence Rate of Distributed Consensus with Nonuniform Delays
    Doan, Thinh T.
    Beck, Carolyn L.
    Srikant, R.
    [J]. 2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 1294 - 1298
12345