Distributed Nonlinear Consensus in the Space of Probability Measures

Select |




Print


Bishop, Adrian; Doucet, Arnaud


2014-08-24


Conference Material


19th World Congress of the International Federation of Automatic Control


Cape Town, South Africa


8662-8668


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


http://www.ifac2014.org


nicta:7893


Bishop, Adrian; Doucet, Arnaud. Distributed Nonlinear Consensus in the Space of Probability Measures. In: 19th World Congress of the International Federation of Automatic Control; Cape Town, South Africa. 2014-08-24. 8662-8668. http://hdl.handle.net/102.100.100/94345?index=1



Loading citation data...

Citation counts
(Requires subscription to view)