多个体网络分布式随机投影无梯度优化算法 distributed random projection gradient-free optimization algorithm for multi-agent networks.pdfVIP

ISSN 1673-9418 CODEN JKYTA8 E-mail: fcst@vip. 163.com Journal of Frontiers of Computer Science and Technology 1673-9418/2016/ 10(11)- 1564-07 Tel: +86-10 doi: 10.3778/j.issn. 1673-9418.1509066 多个体网络分布式随机投影无梯度优化算法* 李德权，陈 平+ 安徽理工大学 理学院，安徽 淮南 232001 Distributed Random Projection Gradient-Free Optimization Algorithm for Multi- Agent Networks* LI Dequan, CHEN Ping+ School of Science, Anhui University of Science and Technology, Huainan, Anhui 232001, China + Corresponding author: E-mail: chenp0554@ LI Dequan, CHEN Ping. Distributed random projection gradient-free optimization algorithm for multi-agent networks. Journal of Frontiers of Computer Science and Technology, 2016, 10(11): 1564-1570. Abstract: This paper proposes a distributed random projection gradient-free optimization algorithm for multi-agent net- works. It is assumed that the objective function of the network is the sum of the objective functions of all individuals, and each individual only knows its own objective function and its own state constraint set. Due to each agent ’s objec- tive function maybe nonconvex, the problem that the subgradient of each agent ’s objective function hard to be calcu- lated can be solved by using the gradient method. Then applying the random projection algorithm at each iteration, the problem of the constrained set maybe unknown or the projection of the constrained set hard to be computed can also be solved. It is proved that, under the proposed algorithm, all agents ’states converge to the optimization set almost surely and the objective function of the network also achieves optimization. Key words: multi-agent network; random proje