Spectral-like gradient method for distributed optimization

被引：0

作者：

Jakovetic, Dusan ^{[1
]}

Krejic, Natasa ^{[1
]}

Jerinkic, Natasa Krklec ^{[1
]}

机构：

[1] Univ Novi Sad, Fac Sci, Dept Math & Informat, Novi Sad, Serbia

来源：

PROCEEDINGS OF 18TH INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES (IEEE EUROCON 2019) | 2019年

关键词：

Distributed optimization; Consensus optimization; Spectral gradient method; Barzilai-Borwein method; BARZILAI; CONSENSUS;

D O I：

10.1109/eurocon.2019.8861761

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We consider a standard distributed multi-agent optimization setting where n nodes (agents) in a network minimize the aggregate sum of their local convex cost functions. We present a distributed spectral-like gradient method, wherein step sizes are node- and iteration-varying, and they are inspired by classical spectral methods from centralized optimization. Simulation examples illustrate the performance of the presented method.

引用

页数：5

共 50 条

[31] On the Convergence of the Conditional Gradient Method in Distributed Optimization Problems
Chernov, A. V.
COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 2011, 51 (09) : 1510 - 1523
[32] Non spurious spectral-like element methods for Maxwell's equations
Cohen, Gary
Durufle, Marc
JOURNAL OF COMPUTATIONAL MATHEMATICS, 2007, 25 (03) : 282 - 304
[33] Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
Hendrikx, Hadrien
Xiao, Lin
Bubeck, Sebastien
Bach, Francis
Massoulie, Laurent
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
[34] Gradient-free method for nonsmooth distributed optimization
Li, Jueyou
Wu, Changzhi
Wu, Zhiyou
Long, Qiang
JOURNAL OF GLOBAL OPTIMIZATION, 2015, 61 (02) : 325 - 340
[35] On the convergence of the conditional gradient method in distributed optimization problems
A. V. Chernov
Computational Mathematics and Mathematical Physics, 2011, 51 : 1510 - 1523
[36] Gradient-free method for nonsmooth distributed optimization
Jueyou Li
Changzhi Wu
Zhiyou Wu
Qiang Long
Journal of Global Optimization, 2015, 61 : 325 - 340
[37] A sixth-order bicompact scheme with spectral-like resolution for hyperbolic equations
Chikitkin, A. V.
Rogov, B. V.
DOKLADY MATHEMATICS, 2017, 96 (02) : 480 - 485
[38] A sixth-order bicompact scheme with spectral-like resolution for hyperbolic equations
A. V. Chikitkin
B. V. Rogov
Doklady Mathematics, 2017, 96 : 480 - 485
[39] An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization
Aybat, N. S.
Wang, Z.
Iyengar, G.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 2454 - 2462
[40] INCREMENTAL GRADIENT-FREE METHOD FOR NONSMOOTH DISTRIBUTED OPTIMIZATION
Li, Jueyou
Li, Guoquan
Wu, Zhiyou
Wu, Changzhi
Wang, Xiangyu
Lee, Jae-Myung
Jung, Kwang-Hyo
JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION, 2017, 13 (04) : 1841 - 1857

← 1 2 3 4 5 →