Universal gradient descent
Optimization and Control
2020-07-20 v9
Abstract
In this book we collect many different and useful facts around gradient descent method. First of all we consider gradient descent with inexact oracle. We build a general model of optimized function that include composite optimization approach, level's methods, proximal methods etc. Then we investigate primal-dual properties of the gradient descent in general model set-up. At the end we generalize method to universal one.
Cite
@article{arxiv.1711.00394,
title = {Universal gradient descent},
author = {Alexander Gasnikov},
journal= {arXiv preprint arXiv:1711.00394},
year = {2020}
}
Comments
MIPT, 291 pages (in Russian)