Convergence Analysis of Distributed Gradient Descent Algorithms With One and Two Momentum Terms

For the centralized optimization, it is well known that adding one momentum term (also called the heavy-ball method) can obtain a faster convergence rate than the gradient method. However, for the distributed counterpart, there is quite few results about the effect of added momentum terms on the con...

Celý popis

Podrobná bibliografie

Vydáno v:	IEEE transactions on cybernetics Ročník 54; číslo 3; s. 1511 - 1522
Hlavní autoři:	Liu, Bing, Chai, Li, Yi, Jingwen
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.03.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Control theory Convergence Convergence rate Cost function distributed optimization Linear programming Momentum momentum term Network topology Newton method Privacy Routh criterion Signal processing algorithms
ISSN:	2168-2267, 2168-2275, 2168-2275
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!