On Preconditioning of Decentralized Gradient-Descent When Solving a System of Linear Equations

This article considers solving an overdetermined system of linear equations in peer-to-peer multiagent networks. The network is assumed to be synchronous and strongly connected. Each agent has a set of local data points, and their goal is to compute a linear model that fits the collective data point...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on control of network systems Jg. 9; H. 2; S. 811 - 822
Hauptverfasser:	Chakrabarti, Kushal, Gupta, Nirupam, Chopra, Nikhil
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.06.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Conditioning Control systems Convergence Data points decision/ estimation theory Distributed algorithms/control Eigenvalues and eigenfunctions Linear equations local pre-conditioning Multiagent systems Network systems optimization Peer-to-peer computing Preconditioning Prediction algorithms Robustness Robustness (mathematics) Social networks State estimation
ISSN:	2325-5870, 2372-2533
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!