Abstract
In this paper, we propose a framework to design a class of fast gradient-based methods in continuous-time that, in comparison with the existing literature including Nesterov's fast-gradient method, features a state-dependent, time-invariant damping term that acts as a feedback control input. The proposed design scheme allows for a user-defined, exponential rate of convergence for a class of nonconvex, unconstrained optimization problems in which the objective function satisfies the so-called Polyak-Łojasiewicz inequality. Formulating the optimization algorithm as a hybrid control system, a state-feedback input is synthesized such that a desired rate of convergence is guaranteed. Furthermore, we establish that the solution trajectories of the hybrid control system are Zeno-free.
Original language | English |
---|---|
Title of host publication | Proceedings of the 57th IEEE Conference on Decision and Control (CDC 2018) |
Editors | Andrew R. Teel, Magnus Egerstedt |
Place of Publication | Piscataway, NJ, USA |
Publisher | IEEE |
Pages | 4078-4083 |
ISBN (Electronic) | 978-1-5386-1395-5 |
DOIs | |
Publication status | Published - 2018 |
Event | CDC 2018: 57th IEEE Conference on Decision and Control - Miami, United States Duration: 17 Dec 2018 → 19 Dec 2018 |
Conference
Conference | CDC 2018: 57th IEEE Conference on Decision and Control |
---|---|
Country/Territory | United States |
City | Miami |
Period | 17/12/18 → 19/12/18 |