Convergence Analysis of a Continuous-Time Distributed Gradient Descent Algorithm

There are various methods designed for solving the distributed optimization problem with only local computation and communication. This letter discusses a continuous-time and distributed version of the gradient descent method for solving the distributed optimization problem. We prove that the conver...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE control systems letters Ročník 5; číslo 4; s. 1339 - 1344
Hlavní autori:	Zhang, Mengyao, Liu, Xinzhi, Liu, Jun
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	IEEE 01.10.2021
Predmet:	Acceleration continuous-time optimization algorithms Convergence convergence analysis distributed gradient descent Distributed optimization Gradient methods Linear programming Multi-agent systems Optimization
ISSN:	2475-1456, 2475-1456
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	There are various methods designed for solving the distributed optimization problem with only local computation and communication. This letter discusses a continuous-time and distributed version of the gradient descent method for solving the distributed optimization problem. We prove that the convergence rate of this method matches those of the centralized gradient descent method and distributed consensus.
ISSN:	2475-1456 2475-1456
DOI:	10.1109/LCSYS.2020.3037038