Problemy Peredachi Informatsii
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Impact factor
Guidelines for authors

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Probl. Peredachi Inf.:
Year:
Volume:
Issue:
Page:
Find






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


Problemy Peredachi Informatsii, 2018, Volume 54, Issue 1, Pages 93–111 (Mi ppi2262)  

This article is cited in 18 scientific papers (total in 18 papers)

Large Systems

Gaussian two-armed bandit and optimization of batch data processing

A. V. Kolnogorov

Department of Applied Mathematics and Information Science, Yaroslav-the-Wise Novgorod State University, Novgorod the Great, Russia
References:
Abstract: We consider the minimax setting for the two-armed bandit problem with normally distributed incomes having a priori unknown mathematical expectations and variances. This setting naturally arises in optimization of batch data processing where two alternative processing methods are available with different a priori unknown efficiencies. During the control process, it is required to determine the most efficient method and ensure its predominant application. We use the main theorem of game theory to search for minimax strategy and minimax risk as Bayesian ones corresponding to the worst-case prior distribution. To find them, a recursive integro-difference equation is obtained. We show that batch data processing almost does not increase the minimax risk if the number of batches is large enough.
Received: 11.09.2017
Revised: 24.11.2017
English version:
Problems of Information Transmission, 2018, Volume 54, Issue 1, Pages 84–100
DOI: https://doi.org/10.1134/S0032946018010076
Bibliographic databases:
Document Type: Article
UDC: 621.391.1+503.5
Language: Russian
Citation: A. V. Kolnogorov, “Gaussian two-armed bandit and optimization of batch data processing”, Probl. Peredachi Inf., 54:1 (2018), 93–111; Problems Inform. Transmission, 54:1 (2018), 84–100
Citation in format AMSBIB
\Bibitem{Kol18}
\by A.~V.~Kolnogorov
\paper Gaussian two-armed bandit and optimization of batch data processing
\jour Probl. Peredachi Inf.
\yr 2018
\vol 54
\issue 1
\pages 93--111
\mathnet{http://mi.mathnet.ru/ppi2262}
\elib{https://elibrary.ru/item.asp?id=32614066}
\transl
\jour Problems Inform. Transmission
\yr 2018
\vol 54
\issue 1
\pages 84--100
\crossref{https://doi.org/10.1134/S0032946018010076}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000429943100007}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85045521102}
Linking options:
  • https://www.mathnet.ru/eng/ppi2262
  • https://www.mathnet.ru/eng/ppi/v54/i1/p93
  • This publication is cited in the following 18 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Проблемы передачи информации Problems of Information Transmission
    Statistics & downloads:
    Abstract page:371
    Full-text PDF :49
    References:40
    First page:16
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024