English

Gradient and gradient-free methods for stochastic convex optimization with inexact oracle

Optimization and Control 2016-03-29 v5

Abstract

In the paper we generalize universal gradient method (Yu. Nesterov) to strongly convex case and to Intermediate gradient method (Devolder-Glineur-Nesterov). We also consider possible generalizations to stochastic and online context. We show how these results can be generalized to gradient-free method and method of random direction search. But the main ingridient of this paper is assumption about the oracle. We considered the oracle to be inexact.

Keywords

Cite

@article{arxiv.1502.06259,
  title  = {Gradient and gradient-free methods for stochastic convex optimization with inexact oracle},
  author = {Alexander Gasnikov and Pavel Dvurechensky and Dmitry Kamzolov},
  journal= {arXiv preprint arXiv:1502.06259},
  year   = {2016}
}

Comments

9 pages, in Russian

R2 v1 2026-06-22T08:34:58.755Z