|
Avtomatika i Telemekhanika, 2017, Issue 2, Pages 36–49
(Mi at14682)
|
|
|
|
This article is cited in 35 scientific papers (total in 35 papers)
Stochastic Systems, Queuing Systems
Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
A. V. Gasnikovab, E. A. Krymovab, A. A. Lagunovskayaca, I. N. Usmanovaab, F. A. Fedorenkoa a Moscow Institute of Physics and Technology (State University), Moscow, Russia
b Institute for Information Transmission Problems (Kharkevich Institute), Russian Academy of Sciences, Moscow, Russia
c Keldysh Institute of Applied Mathematics, Russian Academy of Sciences, Moscow, Russia
Abstract:
In this paper the gradient-free modification of the mirror descent method for convex stochastic online optimization problems is proposed. The crucial assumption in the problem setting is that function realizations are observed with minor noises. The aim of this paper is to derive the convergence rate of the proposed methods and to determine a noise level which does not significantly affect the convergence rate.
Keywords:
online optimization, gradient-free, inexact oracle, stochastic optimization.
Citation:
A. V. Gasnikov, E. A. Krymova, A. A. Lagunovskaya, I. N. Usmanova, F. A. Fedorenko, “Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case”, Avtomat. i Telemekh., 2017, no. 2, 36–49; Autom. Remote Control, 78:2 (2017), 224–234
Linking options:
https://www.mathnet.ru/eng/at14682 https://www.mathnet.ru/eng/at/y2017/i2/p36
|
|