Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization
Optimization and Control
2024-04-16 v2 Machine Learning
Dynamical Systems
Abstract
We introduce an autonomous system with closed-loop damping for first-order convex optimization. While, to this day, optimal rates of convergence are almost exclusively achieved by non-autonomous methods via open-loop damping (e.g., Nesterov's algorithm), we show that our system, featuring a closed-loop damping, exhibits a rate arbitrarily close to the optimal one. We do so by coupling the damping and the speed of convergence of the system via a well-chosen Lyapunov function. By discretizing our system we then derive an algorithm and present numerical experiments supporting our theoretical findings.
Cite
@article{arxiv.2311.10053,
title = {Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization},
author = {Severin Maier and Camille Castera and Peter Ochs},
journal= {arXiv preprint arXiv:2311.10053},
year = {2024}
}