Convergence rates for decentralized consistent location parameter estimation in the presence of Gaussian outliers

We consider a distributed system where sensors make location parameter estimates using their observations. A central processor collects the local estimates and declares a nal estimate based on them. We present a simple study of the convergence properties of three structures where empirical mean and M-estimates are used in various combinations. It is shown that when occasional outliers exist, decentralized estimators that provide robustness at stages where data corruption occurs perform superiorly.