Title :
A stochastic primal-dual algorithm for distributed asynchronous composite optimization
Author :
Bianchi, Pascal ; Hachem, Walid ; Iutzeler, Franck
Author_Institution :
LTCI, Telecom ParisTech, Paris, France
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.
Keywords :
cost reduction; distributed algorithms; multi-agent systems; optimisation; stochastic processes; agents functions; aggregate cost minimizer; coordinate descent; distributed asynchronous composite optimization; primal-dual optimization; private composite function; stochastic primal-dual algorithm; Aggregates; Convergence; Cost function; Distributed algorithms; Signal processing algorithms; Vectors; Consensus algorithms; Coordinate Descent; Distributed optimization; Primal-Dual algorithm;
Conference_Titel :
Signal and Information Processing (GlobalSIP), 2014 IEEE Global Conference on
Conference_Location :
Atlanta, GA
DOI :
10.1109/GlobalSIP.2014.7032215
