Accelerated meta-algorithm for convex optimization
Optimization and Control
2021-03-17 v4
Abstract
We propose an accelerated meta-algorithm, which allows to obtain accelerated methods for convex unconstrained minimization in different settings. As an application of the general scheme we propose nearly optimal methods for minimizing smooth functions with Lipschitz derivatives of an arbitrary order, as well as for smooth minimax optimization problems. The proposed meta-algorithm is more general than the ones in the literature and allows to obtain better convergence rates and practical performance in several settings.
Cite
@article{arxiv.2004.08691,
title = {Accelerated meta-algorithm for convex optimization},
author = {Alexander Gasnikov and Darina Dvinskikh and Pavel Dvurechensky and Dmitry Kamzolov and Vladislav Matykhin and Dmitry Pasechnyk and Nazarii Tupitsa and Alexei Chernov},
journal= {arXiv preprint arXiv:2004.08691},
year = {2021}
}
Comments
25 pages, in Russian