计算机技术与发展Issue(2)：96-100,5.DOI:10.3969/j.issn.1673-629X.2014.02.023
一种基于ADMM的非光滑损失在线优化算法
A New Online Optimization Algorithm for Non-smooth Losses Based on ADMM
摘要
Abstract
Alternating Direction Method of Multipliers (ADMM) already has some practical applications in machine learning problem. In order to adapt to the large-scale data processing and non-smooth loss convex optimization problem,the original batch ADMM has been improved,and propose a new online ADMM with linearized loss function. This new algorithm has a simple operation and efficient compu-ting. Through detailed theoretical analysis,prove the convergence of the new online algorithm and show it has the optimal Regret bound and convergence rate in general convex condition. Finally,compared with the state-of-art algorithms,verify it has efficiency and feasibil-ity.关键词
机器学习/交替方向乘子法/在线优化/大规模/非光滑损失Key words
machine learning/ADMM/online optimization/large-scale/non-smooth loss分类
信息技术与安全科学引用本文复制引用
高乾坤..一种基于ADMM的非光滑损失在线优化算法[J].计算机技术与发展,2014,(2):96-100,5.基金项目
国家自然科学基金资助项目(61273296,60975040) （61273296,60975040）
