期刊
IEEE CONTROL SYSTEMS LETTERS
卷 7, 期 -, 页码 301-306出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LCSYS.2022.3187918
关键词
Radio frequency; Convergence; Linear programming; Perturbation methods; Heuristic algorithms; Lyapunov methods; Control theory; Distributed control; control of networks; optimization; optimization algorithms
资金
- European Research Council (ERC) through the European Union [638992-OPT4SMART]
This article introduces the Gradient Tracking algorithm in the nonconvex distributed consensus optimization framework, and proves its convergence properties through system theoretical analysis.
In this letter we address nonconvex distributed consensus optimization, a popular framework for distributed big-data analytics and learning. We consider the Gradient Tracking algorithm and, by resorting to an elegant system theoretical analysis, we show that agent estimates asymptotically reach consensus to a stationary point. We take advantage of suitable coordinates to write the Gradient Tracking as the interconnection of a fast dynamics and a slow one. To use a singular perturbation analysis, we separately study two auxiliary subsystems called boundary layer and reduced systems, respectively. We provide a Lyapunov function for the boundary layer system and use Lasalle-based arguments to show that trajectories of the reduced system converge to the set of stationary points. Finally, a customized version of a Lasalle's Invariance Principle for singularly perturbed systems is proved to show the convergence properties of the Gradient Tracking.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据