Distributed Optimization of Nonconvex Functions over Time-Varying Graphs
Year: 2019
Type: preprint
Abstract: We consider the distributed optimization problem where a group of agents seeks to cooperatively compute the optimizer of the average of local functions over a time-varying directed communication network. To solve this problem, we propose a novel algorithm which adjusts the ratio between the number of communications and computations to achieve fast convergence. In particular, the iterates of our algorithm converge to the optimizer at the same rate as those of centralized gradient descent in terms of the number of computations. We compare our algorithm with other known algorithms on a distributed target localization problem.
Source: arXiv (Cornell University)
Authors: Bryan Van Scoy, Laurent Lessard
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2947802288
