Distributed saddle-point subgradient algorithms with Laplacian averaging
Abstract
We present distributed subgradient methods for min-max problems with agreement constraints on a subset of the arguments of both the convex and concave parts. Applications include constrained minimization problems where each constraint is a sum of convex functions in the local variables of the agents. In the latter case, the proposed algorithm reduces to primal-dual updates using local subgradients and Laplacian averaging on local copies of the multipliers associated to the global constraints. For the case of general convex-concave saddle-point problems, our analysis establishes the convergence of the running time-averages of the local estimates to a saddle point under periodic connectivity of the communication digraphs. Specifically, choosing the gradient step-sizes in a suitable way, we show that the evaluation error is proportional to , where is the iteration step. We illustrate our results in simulation for an optimization scenario with nonlinear constraints coupling the decisions of agents that cannot communicate directly.
Cite
@article{arxiv.1510.05169,
title = {Distributed saddle-point subgradient algorithms with Laplacian averaging},
author = {David Mateos-Núñez and Jorge Cortés},
journal= {arXiv preprint arXiv:1510.05169},
year = {2016}
}
Comments
15 pages, 4 figures, Proceedings of the IEEE Conference on Decision and Control, Osaka, Japan, 2015