Distributed Computation of Wasserstein Barycenters over Networks
This addresses the challenge of distributed computation for optimal transport problems in networked systems, offering a novel algorithm with theoretical guarantees.
The paper tackles the problem of computing Wasserstein barycenters in a distributed manner over networks, proving that nodes can reach the barycenter through local interactions and providing an estimate for the minimum communication rounds needed to achieve arbitrary precision in solution optimality and consensus.
We propose a new \cu{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 can reach the barycenter of all distributions held in the network by using local interactions compliant with the topology of the graph. We provide an estimate for 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.