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
  • [31] DECENTRALIZED STOCHASTIC NON-CONVEX OPTIMIZATION OVER WEAKLY CONNECTED TIME-VARYING DIGRAPHS
    Lu, Songtao
    Wu, Chai Wah
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 5770 - 5774
  • [32] DECENTRALIZED OPTIMIZATION ON TIME-VARYING DIRECTED GRAPHS UNDER COMMUNICATION CONSTRAINTS
    Chen, Yiyue
    Hashemi, Abolfazl
    Vikalo, Haris
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3670 - 3674
  • [33] Decentralized optimization with affine constraints over time-varying networks
    Yarmoshik, Demyan
    Rogozin, Alexander
    Gasnikov, Alexander
    COMPUTATIONAL MANAGEMENT SCIENCE, 2024, 21 (01)
  • [34] Distributed Learning over Time-Varying Graphs with Adversarial Agents
    Vyavahare, Pooja
    Su, Lili
    Vaidya, Nitin H.
    2019 22ND INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION 2019), 2019,
  • [35] Distributed Gaussian Learning over Time-varying Directed Graphs
    Nedic, Angelia
    Olshevsky, Alex
    Uribe, Cesar A.
    2016 50TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, 2016, : 1710 - 1714
  • [36] Distributed Consensus Kalman Filtering Over Time-Varying Graphs
    Priel, Aviv
    Zelazo, Daniel
    IFAC PAPERSONLINE, 2023, 56 (02): : 10228 - 10233
  • [37] Optimal Distributed Convex Optimization on Slowly Time-Varying Graphs
    Rogozin, Alexander
    Uribe, Cesar A.
    Gasnikov, Alexander, V
    Malkovsky, Nikolay
    Nedic, Angelia
    IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2020, 7 (02): : 829 - 841
  • [38] Distributed Online Convex Optimization on Time-Varying Directed Graphs
    Akbari, Mohammad
    Gharesifard, Bahman
    Linder, Tamas
    IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2017, 4 (03): : 417 - 428
  • [39] DISTRIBUTED NONCONVEX OPTIMIZATION OVER TIME-VARYING NETWORKS
    Di Lorenzo, Paolo
    Scutari, Gesualdo
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 4124 - 4128
  • [40] Event-Triggered Discrete-Time Distributed Consensus Optimization over Time-Varying Graphs
    Lu, Qingguo
    Li, Huaqing
    COMPLEXITY, 2017,