Accelerated and nonaccelerated stochastic gradient descent with inexact model
Optimization and Control
2020-04-16 v2
Abstract
In this paper, we propose a new way to obtain optimal convergence rates for smooth stochastic (strong) convex optimization tasks. Our approach is based on results for optimization tasks where gradients have nonrandom noise. In contrast to previously known results, we extend our idea to the inexact model conception.
Cite
@article{arxiv.2004.04490,
title = {Accelerated and nonaccelerated stochastic gradient descent with inexact model},
author = {Darina Dvinskikh and Alexander Tyurin and Alexander Gasnikov and Sergey Omelchenko},
journal= {arXiv preprint arXiv:2004.04490},
year = {2020}
}
Comments
Withdrawn as this should not have been a new article. Please instead see arXiv:2001.03443