期刊文献+

有向网络异步PUSH-SUM次梯度优化算法的研究 被引量:1

下载PDF
导出
摘要 研究了基于异步信息通信的有向网络分布式Push-sum次梯度优化算法。假定有向网络优化问题目标函数可分解成网络中所有个体各自的目标函数之和,且每个个体仅知道其自身目标函数,并通过与邻居个体进行局部信息异步通信对其自身目标函数进行优化计算,从而协同地使整个网络的优化问题目标函数达到最优。在每个个体目标函数的次梯度有界的条件和随机切换有向网络是一致强连通条件下,证明了Push-Sum次梯度优化算法收敛且其收敛结果为Ο(t Ne-κt+ln t/槡t)。
出处 《皖西学院学报》 2014年第5期11-15,共5页 Journal of West Anhui University
基金 国家自然科学基金(61472003) 国家自然科学青年基金(11401008) 安徽省教育厅自然科学研究重点项目(KJ2014A067)
  • 相关文献

参考文献9

  • 1Tsianos K I,Lawlor S and Rabbat M G. Consensus based Distributed Optimization:Practical Issues and Applications in Large-scale Machine Learning[C]. 50th IEEE Annual Allerton Conference on Communication, Control and Com- puting, 2012 : 1543-1550.
  • 2Gharesifard B and Cortfis J. Continuous-time Distributed Convex Optimization on Weight-balanced Digraphs[C]. 51st IEEE Annual Conference on Decision and Control, 2012:451- 7456.
  • 3Tsitsiklis J N. Problems in Decentralized Decision Making and Computation[R]. Massachusetts Inst of Tech Cam- bridge Lab for Information and Decision Systems, 1984.
  • 4Boyd S, Ghosh A and Prabhakar B. Randomized Gossip A1 gorithms[J]. IEEE Transactions on Information Theory, 2006,52(6) : 2508-2530.
  • 5Dimakis A D G, Sarwate A D and Wainwright M J. Geo- graphic Gossip: Efficient Averaging for Sensor Networks [J]. IEEE Transactions on Signal Processing, 2008, 56 (3) : 1205 -1216.
  • 6Iutzeler F, Ciblat P and Hachem W. Analysis of Sum- weight-like Algorithms for Averaging in Wireless Sensor Networks[J]. IEEE Transactions on Signal Processing, 2013,61(11) : 2802-2814.
  • 7Banfizit F,Blondel V and Thiran P and Tsitsiklis J. Weigh- ted Gossip: Distributed Averaging Using Non-doubly Sto- chastic Matrices [C]. IEEE International Symposium on nformation Theory Proceedings, 2010:1753-1757.
  • 8Nedic A and Olshevsky A. Distributed Optimization over Time-varying Directed Graphs [C]. S2th IEEE Annual Conference on Decision and Control,2013: 6855-6860.
  • 9Lee S and Nedic A. Distributed Random Projection Algo- rithm for Convex Optimization[J]. IEEE Journal of Se- lected Topics in Signal Processing, 2013(7) :221-229.

同被引文献12

  • 1Nedic A,Ozdaglar A.Distributed subgradient methods for Multi-Agent optimization[J].IEEE Transactions on Automatic Control,2009,54(1):48-61.
  • 2ZHU Minghui,MartInez S.On distributed convex optimization under inequality and equality constraints via primal-dual subgradient methods[J].IEEE Trans.autom.control,2010,57(1):151-164.
  • 3YUAN D,XU S,ZHAO H.Distributed Primal-Dual subgradient method for multiagent optimization via consensus algorithms[J].IEEE Transactions on Systems,Man,and Cybernetics.Part B,Cybernetics:a Publication of the IEEE Systems,Man,and Cybernetics Society,2011,41(6):1715-1724.
  • 4YUAN De-ming,XU Sheng-yuan,ZHAO Huan-yu,et al.Distributed dual averaging method for multi-agent optimization with quantized communication[J].Systems&Control Letters,2012,61(11):1053-1061.
  • 5Lee S,Nedic A.Distributed random projection algorithm for convex optimization[J].IEEE Journal of Selected Topics in Signal Processing,2013,7(2):221-229.
  • 6LOU You-cheng,SHI Guo-dong,Johansson K H,et al.Approximate projected consensus for convex intersection computation:convergence analysis and critical error angle[J].IEEE Transactions on Automatic Control,2014,59(7):1722-1736.
  • 7Nesterov Y,Spokoiny V.Random Gradient-Free minimization of convex functions[J].Foundations of Computational Mathematics,2015,36(16):1-40.
  • 8Duchi J C,Jordan M I,Wainwright M J,et al.Optimal rates for Zero-Order convex optimization:the power of two function evaluations[J].IEEE Transactions on Information Theory,2013,61(5):2788-2806.
  • 9YUAN Deming,Ho D W,XU Shengyuan.Zeroth-Order method for distributed optimization with approximate projections[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(2):284-294.
  • 10Nedic A.Olshevsky A.distributed optimization over Time-Varying directed graphs[J].Automatic Control,IEEE Transactions on,2015,60(3):601-615.

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部