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.
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