Avtomatika i Telemekhanika
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Impact factor
Guidelines for authors
Submit a manuscript

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS


Avtomat. i Telemekh.:
Year:
Volume:
Issue:
Page:
Find




Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register

Avtomatika i Telemekhanika, 2017, Issue 2, Pages 36–49 (Mi at14682)  
This article is cited in 34 scientific papers (total in 34 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
Full-text PDF (673 kB) Citations (34)
References:
PDF
HTML
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.
Funding agency Grant number
Russian Foundation for Basic Research 15-31-20571 мол_а_вед
Russian Science Foundation 14-50-00150
This work was supported by the Russian Foundation for Basic Research, project no. 15-31-20571 mol_a_ved. The work of the first two authors was partially supported by the Russian Science Foundation, project no. 14-50-00150 in Institute for Information Transmission Problems of the Russian Academy of Sciences.
Presented by the member of Editorial Board: P. S. Shcherbakov

Received: 16.10.2014
English version:
Automation and Remote Control, 2017, Volume 78, Issue 2, Pages 224–234
DOI: https://doi.org/10.1134/S0005117917020035
Bibliographic databases:
Document Type: Article
Language: Russian
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
Citation in format AMSBIB
\Bibitem{GasKryLag17}
\by A.~V.~Gasnikov, E.~A.~Krymova, A.~A.~Lagunovskaya, I.~N.~Usmanova, F.~A.~Fedorenko
\paper Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
\jour Avtomat. i Telemekh.
\yr 2017
\issue 2
\pages 36--49
\mathnet{http://mi.mathnet.ru/at14682}
\mathscinet{http://mathscinet.ams.org/mathscinet-getitem?mr=3665422}
\elib{https://elibrary.ru/item.asp?id=28903782}
\transl
\jour Autom. Remote Control
\yr 2017
\vol 78
\issue 2
\pages 224--234
\crossref{https://doi.org/10.1134/S0005117917020035}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000394288900003}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85012201490}
Linking options:
  • https://www.mathnet.ru/eng/at14682
  • https://www.mathnet.ru/eng/at/y2017/i2/p36
    • This publication is cited in the following 34 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    		Avtomatika i Telemekhanika
    Statistics & downloads:
    Abstract page:516
    Full-text PDF :125
    References:58
    First page:35
     
      Contact us:
    		  Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024