Accelerated and nonaccelerated stochastic gradient descent with inexact model

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.

Withdrawn as this should not have been a new article. Please instead see arXiv:2001.03443