Asynchronous Gossip Algorithm for Stochastic Optimization: Constant Stepsize Analysis*
作者： S. Sundhar Ram , Angelia Nedić , Venu V. Veeravalli
DOI: 10.1007/978-3-642-12598-0_5
关键词: Gossip 、 Constant (mathematics) 、 Asynchronous communication 、 Network agent 、 Mathematical optimization 、 Stochastic optimization 、 Convex function 、 Mathematics 、 Function (mathematics) 、 Component (UML)
摘要: We consider the problem of minimizing sum convex functions over a network when each component function is known (with stochastic errors) to specific agent. discuss gossip based algorithm [2], and we analyze its error bounds for constant stepsize that uncoordinated across agents.
springer.com
elsevier.com
sci-hub.st 参考文章(3)
S. Boyd, A. Ghosh, B. Prabhakar, D. Shah, Randomized gossip algorithms IEEE Transactions on Information Theory. ,vol. 14, pp. 2508- 2530 ,(2006) , 10.1109/TIT.2006.874516
S. S. Ram, V. V. Veeravalli, A. Nedic, Distributed Non-Autonomous Power Control through Distributed Convex Optimization international conference on computer communications. pp. 3001- 3005 ,(2009) , 10.1109/INFCOM.2009.5062275
S. Sundhar Ram, A. Nedic, V. V. Veeravalli, Asynchronous gossip algorithms for stochastic optimization international conference on game theory for networks. pp. 80- 81 ,(2009) , 10.1109/GAMENETS.2009.5137386