Loopless Variance Reduced Stochastic ADMM for Equality Constrained Problems in IoT Applications

The alternating direction method of multipliers (ADMMs) is an efficient optimization method for solving equality constrained problems in Internet of Things (IoT) applications. Recently, several stochastic variance reduced ADMM algorithms (e.g., SVRG-ADMM) have made exciting progress, such as linear...

Celý popis

Podrobná bibliografie

Vydáno v:	IEEE internet of things journal Ročník 9; číslo 3; s. 2293 - 2303
Hlavní autoři:	Liu, Yuanyuan, Geng, Jiacheng, Shang, Fanhua, An, Weixin, Liu, Hongying, Zhu, Qi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.02.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Alternating direction method of multipliers (ADMMs) Convergence Convex functions Internet of Things loopless algorithm Minimization momentum acceleration Optimization Optimization methods stochastic variance reduced gradient (SVRG) Training Upper bound Variance
ISSN:	2327-4662, 2327-4662
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!