English

Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex

Optimization and Control 2016-04-19 v9

Abstract

In the paper we show that euclidian randomization in some situations (i.e. for gradient-free method on a simplex) can be as good as the randomization on the unit sphere in 1-norm. That is on the simplex example we show that for gradient-free methods the choise of the prox-structure and the choise of a way of randomization have to be connected to each other. We demonstrate how it can be done in an optimal way. It is important that we consider inexact oracle.

Keywords

Cite

@article{arxiv.1412.3890,
  title  = {Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex},
  author = {Alexander Gasnikov and Anastasia Lagunovskaya and Ilnura Usmanova and Fedor Fedorenko},
  journal= {arXiv preprint arXiv:1412.3890},
  year   = {2016}
}

Comments

26 pages, in Russian, Avtomatika i Telemekhanika. 2016

R2 v1 2026-06-22T07:28:45.496Z