Distributed nonlinear consensus in the space of probability measures

Abstract Distributed consensus in the Wasserstein metric space of probability measures is introduced for the first time in this work. It is shown that convergence of the individual agents' measures to a common measure value is guaranteed so long as a weak network connectivity condition is satisfied asymptotically. The common measure achieved asymptotically at each agent is the one closest simultaneously to all initial agent measures in the sense that it minimises a weighted sum of Wasserstein distances between it and all the initial measures. This algorithm has applicability in the field of distributed estimation.