中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 脑图谱与类脑智能实验室
  5. 微观重建与智能分析
Learning With Coefficient-Based Regularized Regression on Markov Resampling

文献类型：期刊论文

作者Li, Luoqing1; Li, Weifu1; Zou, Bin1; Wang, Yulong2,3; Tang, Yuan Yan3; Han, Hua4
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2018-09-01
卷号29期号:9页码:4166-4176
关键词Coefficient-based Regularized Regression (Cbrr) Learning Rate Markov Resampling Uniformly Ergodic Markov Chain (U.e.m.c.)
DOI10.1109/TNNLS.2017.2757140
文献子类Article
英文摘要Big data research has become a globally hot topic in recent years. One of the core problems in big data learning is how to extract effective information from the huge data. In this paper, we propose a Markov resampling algorithm to draw useful samples for handling coefficient-based regularized regression (CBRR) problem. The proposed Markov resampling algorithm is a selective sampling method, which can automatically select uniformly ergodic Markov chain (u.e.M.c.) samples according to transition probabilities. Based on u.e.M.c. samples, we analyze the theoretical performance of CBRR algorithm and generalize the existing results on independent and identically distributed observations. To be specific, when the kernel is infinitely differentiable, the learning rate depending on the sample size m can be arbitrarily close to O(m(-1)) under a mild regularity condition on the regression function. The good generalization ability of the proposed method is validated by experiments on simulated and real data sets.
WOS关键词NEURAL-NETWORKS ; GENERALIZATION PERFORMANCE ; ERROR ANALYSIS ; CLASSIFICATION ; KERNELS ; CHAINS ; OPTIMIZATION ; ALGORITHMS ; TOKAMAK ; MODELS
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000443083700019
资助机构National Natural Science Foundation of China(11771130 ; Strategic Priority Research Program of the CAS(XDB02060000) ; University of Macau(MYRG205(Y1-L4)-FST11-TYY ; Science and Technology Development Fund (FDCT) of Macau(100-2012-A3 ; 11371007 ; MYRG187(Y1-L3)-FST11-TYY ; 026-2013-A) ; 61702057 ; RDG009/FST-TYY/2012) ; 61273244)
源URL[http://ir.ia.ac.cn/handle/173211/21825]  
专题类脑智能研究中心_微观重建与智能分析
作者单位1.Hubei Univ, Fac Math & Stat, Hubei Key Lab Appl Math, Wuhan 430062, Hubei, Peoples R China
2.Chengdu Univ, Sch Informat Sci & Engn, Chengdu 610106, Sichuan, Peoples R China
3.Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China
4.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Li, Luoqing,Li, Weifu,Zou, Bin,et al. Learning With Coefficient-Based Regularized Regression on Markov Resampling[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(9):4166-4176.
APA Li, Luoqing,Li, Weifu,Zou, Bin,Wang, Yulong,Tang, Yuan Yan,&Han, Hua.(2018).Learning With Coefficient-Based Regularized Regression on Markov Resampling.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(9),4166-4176.
MLA Li, Luoqing,et al."Learning With Coefficient-Based Regularized Regression on Markov Resampling".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.9(2018):4166-4176.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。