A stochastic primal-dual algorithm for distributed asynchronous composite optimization

Pascal Bianchi, Walid Hachem, Franck Iutzeler

Abstract: Consider a network where each agent has a private composite function (e.g. the sum of a smooth and a non-smooth function). The problem we address here is to And a minimize! of the aggregate cost (the sum of the agents functions) in a distributed manner. In this paper, we combine recent results on primal-dual optimization and coordinate descent to propose an asynchronous distributed algorithm for composite optimization.