Estimate exchange over network is good for distributed hard thresholding pursuit

作     者：Zaki, Ahmed Mitra, Partha P. Rasmussen, Lars K. Chatterjee, Saikat 

作者机构：KTH Royal Inst Technol Sch Elect Engn Stockholm Sweden Cold Spring Harbor Lab 1 Bungtown Rd New York NY USA 

出 版 物：《SIGNAL PROCESSING》 (信号处理)

年 卷 期：2019年第156卷

页      面：1-11页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

主　　题：Sparse learning Distributed algorithm Greedy pursuit algorithm RIP analysis 

摘      要：We investigate an existing distributed algorithm for learning sparse signals or data over networks. The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network. This learning strategy using exchange of intermediate estimates over the network requires a limited communication overhead for information transmission. Our objective in this article is to show that the strategy is good for learning in spite of limited communication. In pursuit of this objective, we first provide a restricted isometry property (RIP)-based theoretical analysis on convergence of the iterative algorithm. Then, using simulations, we show that the algorithm provides competitive performance in learning sparse signals vis-a-vis an existing alternate distributed algorithm. The alternate distributed algorithm exchanges more information including observations and system parameters. (C) 2018 Elsevier B.V. All rights reserved.