An optimal gradient method for smooth strongly convex minimization
Abstract
We present an optimal gradient method for smooth strongly convex optimization. The method is optimal in the sense that its worst-case bound on the distance to an optimal point exactly matches the lower bound on the oracle complexity for the class of problems, meaning that no black-box first-order method can have a better worst-case guarantee without further assumptions on the class of problems at hand. In addition, we provide a constructive recipe for obtaining the algorithmic parameters of the method and illustrate that it can be used for deriving methods for other optimality criteria as well.
Cite
@article{arxiv.2101.09741,
title = {An optimal gradient method for smooth strongly convex minimization},
author = {Adrien Taylor and Yoel Drori},
journal= {arXiv preprint arXiv:2101.09741},
year = {2022}
}
Comments
Accepted for publication in Mathematical Programming. Codes available at https://github.com/AdrienTaylor/Optimal-Gradient-Method (symbolic verifications and numerical experiments)