Accelerated Variance Reduction Stochastic ADMM for Large-Scale Machine Learning

Yuanyuan Liu,Fanhua Shang,Hongying Liu,Lin Kong,Jiao Licheng,Zhouchen Lin

IEEE Transactions on Pattern Analysis and Machine Intelligence（2021）

引用 20|浏览1792

暂无评分

摘要

Recently, many stochastic variance reduced alternating direction methods of multipliers (ADMMs) (e.g., SAG-ADMM and SVRG-ADMM) have made exciting progress such as linear convergence rate for strongly convex (SC) problems. However, their best-known convergence rate for non-strongly convex (non-SC) problems is $\mathcal {O}(1/T)$更多

查看译文

关键词

Convex functions,Acceleration,Convergence,Stochastic processes,Optimization,Machine learning,Complexity theory

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