Distributed Computation of Wasserstein Barycenters over Networks
We propose a new class-optimal algorithm for the distributed computation of Wasserstein Barycenters over networks. Assuming that each node in a graph has a probability distribution, we prove that every node is able to reach the barycenter of all distributions held in the network by using local interactions compliant with the topology of the graph. We show the minimum number of communication rounds required for the proposed method to achieve arbitrary relative precision both in the optimality of the solution and the consensus among all agents for undirected fixed networks.
READ FULL TEXT