Matematicheskie Zametki
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Forthcoming papers
Archive
Impact factor
Guidelines for authors
License agreement
Submit a manuscript

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Mat. Zametki:
Year:
Volume:
Issue:
Page:
Find






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


Matematicheskie Zametki, 2020, Volume 108, Issue 4, Pages 515–528
DOI: https://doi.org/10.4213/mzm12751
(Mi mzm12751)
 

This article is cited in 7 scientific papers (total in 7 papers)

Accelerated and Unaccelerated Stochastic Gradient Descent in Model Generality

D. M. Dvinskikhabc, A. I. Turind, A. V. Gasnikovbcd, S. S. Omelchenkob

a Weierstrass Institute
b Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Moscow Region
c Institute for Information Transmission Problems of the Russian Academy of Sciences (Kharkevich Institute), Moscow
d National Research University "Higher School of Economics", Moscow
Full-text PDF (571 kB) Citations (7)
References:
Abstract: A new method for deriving estimates of the rate of convergence of optimal methods for solving problems of smooth (strongly) convex stochastic optimization is described. The method is based on the results of stochastic optimization derived from results on the convergence of optimal methods under the conditions of inexact gradients with small noises of nonrandom nature. In contrast to earlier results, all estimates in the present paper are obtained in model generality.
Keywords: stochastic optimization, accelerated gradient descent, model generality, composite optimization.
Funding agency Grant number
Russian Foundation for Basic Research 19-31-90062
18-31-20005 мол_а_вед
Ministry of Science and Higher Education of the Russian Federation 075-00337-20-03
The research of D. M. Dvinskikh in Sec. 1 was supported by the Ministry of Science and Higher Education of the Russian Federation under grant no. 075-00337-20-03, project no. 0714-2020-0005. The research of A. I. Tyurin in Sec. 3 was supported by the Russian Foundation for Basic Research under grant 19-31-90062. The research of A. V. Gasnikov in Sec. 2 was supported by the Russian Foundation for Basic Research under grant 18-31-20005 mol_a_ved.
Received: 11.04.2020
Revised: 20.05.2020
English version:
Mathematical Notes, 2020, Volume 108, Issue 4, Pages 511–522
DOI: https://doi.org/10.1134/S0001434620090230
Bibliographic databases:
Document Type: Article
UDC: 519.85
Language: Russian
Citation: D. M. Dvinskikh, A. I. Turin, A. V. Gasnikov, S. S. Omelchenko, “Accelerated and Unaccelerated Stochastic Gradient Descent in Model Generality”, Mat. Zametki, 108:4 (2020), 515–528; Math. Notes, 108:4 (2020), 511–522
Citation in format AMSBIB
\Bibitem{DviTurGas20}
\by D.~M.~Dvinskikh, A.~I.~Turin, A.~V.~Gasnikov, S.~S.~Omelchenko
\paper Accelerated and Unaccelerated Stochastic Gradient Descent in Model Generality
\jour Mat. Zametki
\yr 2020
\vol 108
\issue 4
\pages 515--528
\mathnet{http://mi.mathnet.ru/mzm12751}
\crossref{https://doi.org/10.4213/mzm12751}
\mathscinet{http://mathscinet.ams.org/mathscinet-getitem?mr=4153684}
\elib{https://elibrary.ru/item.asp?id=45228685}
\transl
\jour Math. Notes
\yr 2020
\vol 108
\issue 4
\pages 511--522
\crossref{https://doi.org/10.1134/S0001434620090230}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000584617700023}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85094120094}
Linking options:
  • https://www.mathnet.ru/eng/mzm12751
  • https://doi.org/10.4213/mzm12751
  • https://www.mathnet.ru/eng/mzm/v108/i4/p515
  • This publication is cited in the following 7 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Математические заметки Mathematical Notes
    Statistics & downloads:
    Abstract page:343
    Full-text PDF :141
    References:48
    First page:10
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024