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

Yuanyuan Liu,Jiacheng Geng,Fanhua Shang,Weixin An,Hongying Liu,Qi Zhu

IEEE Internet of Things Journal（2022）

引用 2|浏览26

暂无评分

摘要

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 convergence for strongly convex (SC) problems. However, SVRG-ADMM and its variants have an outer loo...

查看译文

关键词

Convergence,Internet of Things,Convex functions,Optimization methods,Upper bound,Training,Minimization

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要