An Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs

被引:5
|
作者
Rogozin, Alexander [1 ,2 ]
Bochko, Mikhail [1 ,2 ]
Dvurechensky, Pavel [3 ,4 ]
Gasnikov, Alexander [5 ]
Lukoshkin, Vladislav [6 ]
机构
[1] Moscow Inst Phys & Technol, Moscow, Russia
[2] HSE Univ, Moscow, Russia
[3] Weierstrass Inst Appl Anal & Stochast, Berlin, Germany
[4] HSE Univ, Inst Informat Transmiss Problems RAS, Moscow, Russia
[5] HSE Univ, Inst Informat Transmiss Problems RAS, Moscow Inst Phys & Technol, Moscow, Russia
[6] Skolkovo Inst Sci & Technol, Moscow, Russia
关键词
stochastic optimization; decentralized distributed optimization; time-varying network; INTERMEDIATE GRADIENT-METHOD; ASYMPTOTIC AGREEMENT; CONVEX; ALGORITHMS; CONVERGENCE;
D O I
10.1109/CDC45484.2021.9683110
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We consider a distributed stochastic optimization problem that is solved by a decentralized network of agents with only local communication between neighboring agents. The goal of the whole system is to minimize a global objective function given as a sum of local objectives held by each agent. Each local objective is defined as an expectation of a convex smooth random function and the agent is allowed to sample stochastic gradients for this function. For this setting we propose the first accelerated (in the sense of Nesterov's acceleration) method that simultaneously attains optimal up to a logarithmic factor communication and oracle complexity bounds for smooth strongly convex distributed stochastic optimization. We also consider the case when the communication graph is allowed to vary with time and obtain complexity bounds for our algorithm, which are the first upper complexity bounds for this setting in the literature.
引用
收藏
页码:3367 / 3373
页数:7
相关论文
共 50 条
  • [41] Decentralized synchronization of time-varying oscillators under time-varying bidirectional graphs
    Maghenem, Mohamed
    Lekefouet, Hermann
    Loria, Antonio
    Panteley, Elena
    2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, : 4018 - 4023
  • [42] Analysis and Design of First-Order Distributed Optimization Algorithms Over Time-Varying Graphs
    Sundararajan, Akhil
    Van Scoy, Bryan
    Lessard, Laurent
    IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2020, 7 (04): : 1597 - 1608
  • [43] Distributed constrained optimization algorithms with linear convergence rate over time-varying unbalanced graphs☆
    Liu, Hongzhe
    Yu, Wenwu
    Zheng, Wei Xing
    Nedic, Angelia
    Zhu, Yanan
    AUTOMATICA, 2024, 159
  • [44] Privacy-Preserving Optimization Algorithm for Distributed Energy Management Over Time-Varying Graphs: A State Decomposition Method
    Luan, Meng
    Wen, Guanghui
    Yang, Tao
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2024,
  • [45] Distributed Stochastic Constrained Composite Optimization Over Time-Varying Network With a Class of Communication Noise
    Yu, Zhan
    Ho, Daniel W. C.
    Yuan, Deming
    Liu, Jie
    IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (06) : 3561 - 3573
  • [46] Distributed Optimization of Strongly Convex Functions on Directed Time-Varying Graphs
    Nedic, Angelia
    Olshevsky, Alex
    2013 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2013, : 329 - 332
  • [47] Distributed nonconvex constrained optimization over time-varying digraphs
    Scutari, Gesualdo
    Sun, Ying
    MATHEMATICAL PROGRAMMING, 2019, 176 (1-2) : 497 - 544
  • [48] Distributed nonconvex constrained optimization over time-varying digraphs
    Gesualdo Scutari
    Ying Sun
    Mathematical Programming, 2019, 176 : 497 - 544
  • [49] Distributed Nonconvex Multiagent Optimization Over Time-Varying Networks
    Sun, Ying
    Scutari, Gesualdo
    Palomar, Daniel
    2016 50TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, 2016, : 788 - 794
  • [50] Accelerated AB/Push-Pull Methods for Distributed Optimization Over Time-Varying Directed Networks
    Nguyen, Duong Thuy Anh
    Nguyen, Duong Tung
    Nedic, Angelia
    IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2024, 11 (03): : 1395 - 1407