2020/10/20 by Eduardo Mojica-Nava, Mojica-Nava, Eduardo, David Yanguas-Rojas +3
Computer Science · Mathematics · #Distributed #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Multiagent Systems (cs.MA) #Optimization and Control (math.OC) #Parallel #Social and Information Networks (cs.SI) #and Cluster Computing (cs.DC) #cs.DC #cs.MA #cs.SI #math.OC #stat.ML
paper · pdf · doi:10.48550/arxiv.2010.09993
Submitted to ACC2021
arxiv created 2020/10/20 · arxiv updated 2020/10/21
We consider the model of cooperative learning via distributed non-Bayesian learning, where a network of agents tries to jointly agree on a hypothesis that best described a sequence of locally available observations. Building upon recently proposed weak communication network models, we propose a robust cooperative learning rule that allows asynchronous communications, message delays, unpredictable message losses, and directed communication among nodes. We show that our proposed learning dynamics guarantee that all agents in the network will have an asymptotic exponential decay of their beliefs on the wrong hypothesis, indicating that the beliefs of all agents will concentrate on the optimal hypotheses. Numerical experiments provide evidence on a number of network setups.