| 王俊雅.切换网络下加速分布式在线加权对偶平均算法[J].井冈山大学自然版,2018,(4):6-10 |
| 切换网络下加速分布式在线加权对偶平均算法 |
| ACCELERATE DISTRIBUTED ONLINE WEIGHTED DUAL AVERAGE ALGORITHM IN SWITCHED NETWORKS |
| 投稿时间：2018-05-05 修订日期：2018-06-27 |
| DOI：10.3969/j.issn.1674-8085.2018.04.002 |
| 中文关键词: 分布式 加权 切换网络 对偶平均 Regret界 |
| 英文关键词: distributed weighted switched network dual average Regret bound |
| 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） |
|
| 摘要点击次数: 1581 |
| 全文下载次数: 1938 |
| 中文摘要: |
| 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。 |
| 英文摘要: |
| 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. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
