| 切换网络下加速分布式在线加权对偶平均算法 |
| |
| 引用本文： | 王俊雅.切换网络下加速分布式在线加权对偶平均算法[J].井冈山大学学报（自然科学版）,2018(4):6-10. |
| |
| 作者姓名： | 王俊雅 |
| |
| 作者单位： | 安徽理工大学数学与大数据学院, 安徽, 淮南 232000 |
| |
| 基金项目： | 安徽省级精品资源共享课程（11528）；硕士研究生创新基金项目（2017CX2046） |
| |
| 摘 要： | 研究了切换网络下加速分布式在线加权对偶平均算法,提出了A-DOWDA算法。首先利用加权因子对对偶变量进行加权,其次在有向切换网络是周期强连通,且对应的邻接矩阵是随机的而非双随机的条件下,加速了算法的收敛速率,最后通过数值实验验证了算法的可行性。
|
| 关 键 词： | 分布式 加权 切换网络 对偶平均 Regret界 |
| 收稿时间： | 2018/5/5 0:00:00 |
| 修稿时间： | 2018/6/27 0:00:00 |
ACCELERATE DISTRIBUTED ONLINE WEIGHTED DUAL AVERAGE ALGORITHM IN SWITCHED NETWORKS |
| |
| WANG Jun-ya.ACCELERATE DISTRIBUTED ONLINE WEIGHTED DUAL AVERAGE ALGORITHM IN SWITCHED NETWORKS[J].Journal of Jinggangshan University(Natural Sciences Edition),2018(4):6-10. |
| |
| Authors: | WANG Jun-ya |
| |
| Institution: | College of Mathematics and Big Data, Anhui University of Science and Technology, Huainan, Anhui 232000, China |
| |
| Abstract: | We studies the distributed online weighted dual average algorithm is accelerated under switched network and an A-DWDA algorithm is proposed. Firstly, weighting factors are used to weight dual variables. Secondly, the directed switched network is periodically strongly connected, and the corresponding adjacency matrix is stochastic rather than doubly stochastic, the convergence speed of the algorithm is accelerated. Finally, a numerical experiment is performed to verify the effectiveness of the proposed algorithm. |
| |
| Keywords: | distributed weighted switched network dual average Regret bound |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《井冈山大学学报（自然科学版）》浏览原始摘要信息 |
| 点击此处可从《井冈山大学学报（自然科学版）》下载免费的PDF全文 |
