Distributed non-convex optimization of multi-agent systems using boosting functions to escape local optima
Files
Accepted manuscript
Date
2020-07
Authors
Welikala, Shirantha
Cassandras, Christos G.
Version
Accepted manuscript
OA Version
Citation
Shirantha Welikala, Christos G Cassandras. 2020. "Distributed Non-convex Optimization of Multi-agent Systems Using Boosting Functions to Escape Local Optima." 2020 American Control Conference (ACC). 2020 American Control Conference (ACC). 2020-07-01 - 2020-07-03. https://doi.org/10.23919/acc45564.2020.9147395
Abstract
We address the problem of multiple local optima arising in cooperative multi-agent optimization problems with non-convex objective functions. We propose a systematic approach to escape these local optima using boosting functions. These functions temporarily transform a gradient at a local optimum into a "boosted" non-zero gradient. Extending a prior centralized optimization approach, we develop a distributed framework for the use of boosted gradients and show that convergence of this distributed process can be attained by employing an optimal variable step size scheme for gradient-based algorithms. Numerical examples are included to show how the performance of a class of multi-agent optimization systems can be improved.