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
  • [21] An Event-Based Delayed Projection Row-Stochastic Method for Distributed Constrained Optimization Over Time-Varying Graphs
    Xing, Mingqi
    Ma, Dazhong
    Zhang, Huaguang
    Xie, Xiangpeng
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, 54 (12): : 7508 - 7520
  • [22] Decentralized Conditional Gradient Method on Time-Varying Graphs
    Vedernikov, R. A.
    Rogozin, A. V.
    Gasnikov, A. V.
    PROGRAMMING AND COMPUTER SOFTWARE, 2023, 49 (06) : 505 - 512
  • [23] Decentralized Conditional Gradient Method on Time-Varying Graphs
    R. A. Vedernikov
    A. V. Rogozin
    A. V. Gasnikov
    Programming and Computer Software, 2023, 49 : 505 - 512
  • [24] A Distributed Optimization Algorithm over Time-Varying Graphs with Efficient Gradient Evaluations
    Van Scoy, Bryan
    Lessard, Laurent
    IFAC PAPERSONLINE, 2019, 52 (20): : 357 - 362
  • [25] Distributed Optimization with Binary Relative Information over Deterministically Time-varying Graphs
    Zhang, Jiaqi
    You, Keyou
    2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 2747 - 2752
  • [26] DISTRIBUTED CONVEX OPTIMIZATION WITH COUPLING CONSTRAINTS OVER TIME-VARYING DIRECTED GRAPHS
    Zhang, Bingru
    Gu, Chuanye
    Li, Jueyou
    JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION, 2021, 17 (04) : 2119 - 2138
  • [27] Byzantine-robust decentralized stochastic optimization over static and time-varying networks
    Peng, Jie
    Li, Weiyu
    Ling, Qing
    SIGNAL PROCESSING, 2021, 183
  • [28] A Fast Row-Stochastic Decentralized Method for Distributed Optimization Over Directed Graphs
    Ghaderyan, Diyako
    Aybat, Necdet Serhat
    Aguiar, A. Pedro
    Pereira, Fernando Lobo
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (01) : 275 - 289
  • [29] Distributed Stochastic Optimization with Gradient Tracking over Time-Varying Directed Networks
    Duong Thuy
    Anh Nguyen
    Duong Tung Nguyen
    Nedic, Angelia
    FIFTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, IEEECONF, 2023, : 1605 - 1609
  • [30] Accelerated Convergence Algorithm for Distributed Constrained Optimization under Time-Varying General Directed Graphs
    Li, Huaqing
    Lu, Qingguo
    Liao, Xiaofeng
    Huang, Tingwen
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2020, 50 (07): : 2612 - 2622