Title
Coordinate Dual Averaging for Decentralized Online Optimization With Nonseparable Global Objectives.
Abstract
We consider a decentralized online convex optimization problem in a network of agents, where each agent controls only a coordinate (or a part) of the global decision vector. For such a problem, we propose two decentralized variants (ODA-C and ODA-PS) of Nesterov's primal-dual algorithm with dual averaging. In ODA-C, to mitigate the disagreements on the primal-vector updates, the agents implement a...
Year
DOI
Venue
2018
10.1109/TCNS.2016.2573639
IEEE Transactions on Control of Network Systems
Keywords
Field
DocType
Optimization,Linear programming,Resource management,Algorithm design and analysis,Convex functions,Control systems,Signal processing algorithms
Sublinear function,Discrete mathematics,Mathematical optimization,Time horizon,Algorithm design,Control theory,Multi-agent system,Convex function,Linear programming,Lipschitz continuity,Convex optimization,Mathematics
Journal
Volume
Issue
ISSN
5
1
2325-5870
Citations 
PageRank 
References 
3
0.39
21
Authors
3
Name
Order
Citations
PageRank
Soo-Min Lee114812.00
Angelia Nedic22323148.65
Maxim Raginsky377160.65