模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2016, Vol. 29 Issue (7): 577-589    DOI: 10.16451/j.cnki.issn1003-6059.201607001
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Stochastic Algorithm with Reduced Variance and Weighted Average for Solving Non-smooth Strongly Convex Optimization Problems
ZHU Xiaohui, TAO Qing
11st Department, Army Officer Academy of PLA, Hefei 230031

Download: PDF (556 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Using the strategy of reducing the variance in smooth stochastic method can effectively improve the convergence of the algorithm. An algorithm, hybrid regularized mirror descent with reduced variance and weighted average (α-HRMDVR-W), is obtained by using weighted average and reduced variance for solving “L1+ L2 + Hinge” non-smooth strong convex optimization problem. The variance reduction strategies are utilized at each step of the iterative process, and the weighted average of the output mode is used. It is proved that the α-HRMDVR-W has optimal convergence rate and the convergence rate does not depend on the number of samples. Unlike the existing variance reduction methods, α-HRMDVR-W only uses a small portion of samples instead of the total samples to modify the gradient at each iteration. Experimental results show that α-HRMDVR-W reduces the variance and decreases CPU time.
Key wordsMachine Learning      Stochastic Optimization      Reduced Variance     
Received: 01 March 2016     
ZTFLH: TP 301  
About author:: ZHU Xiaohui(Corresponding author), born in 1989, master student. His research interests include pattern recognition.TAO Qing, born in 1965, Ph.D., professor. His research interests include pattern recognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHU Xiaohui
TAO Qing
Cite this article:   
ZHU Xiaohui,TAO Qing. Stochastic Algorithm with Reduced Variance and Weighted Average for Solving Non-smooth Strongly Convex Optimization Problems[J]. , 2016, 29(7): 577-589.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201607001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2016/V29/I7/577
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn