Exponentially Converging Distributed Gradient Descent with Intermittent Communication via Hybrid Methods

We present a hybrid systems framework for multi-agent optimization in which agents execute computations in continuous time and communicate in discrete time. The optimization algorithm is a hybrid version of parallelized coordinate descent. Agents implement a sample-and-hold strategy in which gradients are computed at communication times and held constant during flows between communications. Completeness of maximal solutions under these hybrid dynamics is established. Under assumptions of smoothness and strong convexity, we show that this system exponentially converges to the minimizer of an objective function. Simulation results illustrate this convergence rate.

[1]  Bahman Gharesifard,et al.  Distributed Continuous-Time Convex Optimization on Weight-Balanced Digraphs , 2012, IEEE Transactions on Automatic Control.

[2]  P. Olver Nonlinear Systems , 2013 .

[3]  Jean-Yves Audibert Optimization for Machine Learning , 1995 .

[4]  Sonia Martínez,et al.  Distributed convex optimization via continuous-time coordination algorithms with discrete-time communication , 2014, Autom..

[5]  Ricardo G. Sanfelice,et al.  Robust distributed synchronization of networked linear systems with intermittent information , 2019, Autom..

[6]  Jan Swevers,et al.  Time-Optimal Path Tracking for Robots: A Convex Optimization Approach , 2009, IEEE Transactions on Automatic Control.

[7]  Stephen P. Boyd,et al.  A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights , 2014, J. Mach. Learn. Res..

[8]  Dimitra Panagou,et al.  Fixed-Time Stable Gradient Flows: Applications to Continuous-Time Optimization , 2018, IEEE Transactions on Automatic Control.

[9]  Ricardo G. Sanfelice,et al.  A toolbox for simulation of hybrid systems in matlab/simulink: hybrid equations (HyEQ) toolbox , 2013, HSCC '13.

[10]  Wei Ren,et al.  Distributed Continuous-Time Convex Optimization With Time-Varying Cost Functions , 2017, IEEE Transactions on Automatic Control.

[11]  Reza Olfati-Saber,et al.  Consensus and Cooperation in Networked Multi-Agent Systems , 2007, Proceedings of the IEEE.

[12]  Wei Yu,et al.  An introduction to convex optimization for communications and signal processing , 2006, IEEE Journal on Selected Areas in Communications.

[13]  Choon Yik Tang,et al.  Zero-Gradient-Sum Algorithms for Distributed Convex Optimization: The Continuous-Time Case , 2011, IEEE Transactions on Automatic Control.

[14]  Sonia Martínez,et al.  Coverage control for mobile sensing networks , 2002, IEEE Transactions on Robotics and Automation.

[15]  Pedro Casau,et al.  Analysis and design of event-triggered control algorithms using hybrid systems tools , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).