On the Linear Convergence of Distributed Optimization over Directed Graphs

MaRDI QIDQ6266206zbMATH OpenFDO

Authors Chenguang Xi, Usman A. Khan

Publication date 7 October 2015

Abstract: This paper develops a fast distributed algorithm, termed emph{DEXTRA}, to solve the optimization problem when~$n$ agents reach agreement and collaboratively minimize the sum of their local objective functions over the network, where the communication between the agents is described by a~emph{directed} graph. Existing algorithms solve the problem restricted to directed graphs with convergence rates of $O(lnk/sqrtk)$ for general convex objective functions and $O(lnk/k)$ when the objective functions are strongly-convex, where~$k$ is the number of iterations. We show that, with the appropriate step-size, DEXTRA converges at a linear rate $O(a{u}^k)$ for $0<au<1$, given that the objective functions are restricted strongly-convex. The implementation of DEXTRA requires each agent to know its local out-degree. Simulation examples further illustrate our findings.

This page was built for publication: On the Linear Convergence of Distributed Optimization over Directed Graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6266206)