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

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE control systems letters Ročník 5; číslo 4; s. 1339 - 1344
Hlavní autoři: Zhang, Mengyao, Liu, Xinzhi, Liu, Jun
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.10.2021
Témata:
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 přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
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