An Improved Convergence Analysis for Decentralized Online Stochastic Non-Convex Optimization

In this paper, we study decentralized online stochastic non-convex optimization over a network of nodes. Integrating a technique called gradient tracking in decentralized stochastic gradient descent, we show that the resulting algorithm, GT-DSGD , enjoys certain desirable characteristics towards min...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on signal processing Ročník 69; s. 1842 - 1858
Hlavní autori:	Xin, Ran, Khan, Usman A., Kar, Soummya
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Algorithms Asymptotic properties Computational geometry Convergence Convex analysis Convexity Decentralized optimization Linear programming multi-agent systems non-convex problems Optimization Signal processing algorithms Steady-state stochastic gradient methods Stochastic processes Transient analysis
ISSN:	1053-587X, 1941-0476
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!