Accelerated and nonaccelerated stochastic gradient descent with model conception
Optimization and Control
2020-07-14 v5
Abstract
In this paper, we describe a new way to get convergence rates for optimal methods in smooth (strongly) convex optimization tasks. Our approach is based on results for tasks where gradients have nonrandom small noises. Unlike previous results, we obtain convergence rates with model conception.
Cite
@article{arxiv.2001.03443,
title = {Accelerated and nonaccelerated stochastic gradient descent with model conception},
author = {Darina Dvinskikh and Alexander Tyurin and Alexander Gasnikov and Sergey Omelchenko},
journal= {arXiv preprint arXiv:2001.03443},
year = {2020}
}
Comments
in Russian