Learning a Coupled Linearized Method in Online Setting
Xue, Wei1; Zhang, Wensheng1,2
2017-02-01
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷号28期号:2页码:438-450
文章类型Article
摘要Based on the alternating direction method of multipliers, in this paper, we propose, analyze, and test a coupled linearized method, which aims to minimize an unconstrained problem consisting of a loss term and a regularization term in an online setting. To solve this problem, we first transform it into an equivalent constrained minimization problem with a separable structure. Then, we split the corresponding augmented Lagrangian function and minimize the resulting subproblems distributedly with one variable by fixing another one. This method is easy to execute without calculating matrix inversion by implementing three linearized operations per iteration, and at each iteration, we can obtain a closed-form solution. In particular, our update rule contains the well-known soft-thresholding operator as a special case. Moreover, upper bound on the regret of the proposed method is analyzed. Under some mild conditions, it can achieve 0(1/ root T) convergence rate for convex learning problems and 0((logT)/ T) for strongly convex learning. Numerical experiments and comparisons with several state-of-the-art methods are reported, which demonstrate the efficiency and effectiveness of our approach.
关键词Alternating Minimization Convex Optimization Linearized Operation Online Learning Regret Bound
WOS标题词Science & Technology ; Technology
DOI10.1109/TNNLS.2016.2514413
关键词[WOS]OPTIMIZATION METHODS ; ALGORITHM ; REGRESSION ; SHRINKAGE ; SELECTION
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(U1135005 ; Project of Post-Graduate Scientific Research Innovation Program of Jiangsu Province(KYZZ15_0123) ; 61305018 ; 61432008 ; 61472423 ; 61532006)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000394522900017
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/14383
专题精密感知与控制研究中心_人工智能与机器学习
作者单位1.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Jiangsu, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Xue, Wei,Zhang, Wensheng. Learning a Coupled Linearized Method in Online Setting[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(2):438-450.
APA Xue, Wei,&Zhang, Wensheng.(2017).Learning a Coupled Linearized Method in Online Setting.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(2),438-450.
MLA Xue, Wei,et al."Learning a Coupled Linearized Method in Online Setting".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.2(2017):438-450.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xue, Wei]的文章
[Zhang, Wensheng]的文章
百度学术
百度学术中相似的文章
[Xue, Wei]的文章
[Zhang, Wensheng]的文章
必应学术
必应学术中相似的文章
[Xue, Wei]的文章
[Zhang, Wensheng]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。