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, 2021, Issue 10, Pages 60–75
DOI: https://doi.org/10.31857/S0005231021100068
(Mi at15800)
 

Solving convex min-min problems with smoothness and strong convexity in one group of variables and low dimension in the other

E. L. Gladinab, M. Alkousaba, A. V. Gasnikovab

a Moscow Institute of Physics and Technology, Dolgoprudnyi, Moscow oblast, 141701 Russia
b Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, 127051 Russia
References:
Abstract: The article deals with some approaches to solving convex problems of the min-min type with smoothness and strong convexity in only one of the two groups of variables. It is shown that the proposed approaches based on Vaidya’s method, the fast gradient method, and the accelerated gradient method with variance reduction have linear convergence. It is proposed to use Vaidya’s method to solve the exterior problem and the fast gradient method to solve the interior (smooth and strongly convex) one. Due to its importance for applications in machine learning, the case where the objective function is the sum of a large number of functions is considered separately. In this case, the accelerated gradient method with variance reduction is used instead of the fast gradient method. The results of numerical experiments are presented that illustrate the advantages of the proposed procedures for a logistic regression problem in which the a priori distribution for one of the two groups of variables is available.
Keywords: convex optimization, cutting plane method, Vaidya’s method, variance reduction, fast gradient method, logistic regression.
Funding agency Grant number
Ministry of Science and Higher Education of the Russian Federation 075-00337-20-03, номер проекта 0714-2020-0005
Russian Foundation for Basic Research 18-29-03071_мк
This work was supported by the Ministry of Science and Higher Education of the Russian Federation, state assignment no. 075-00337-20-03, project no.0714-2020-0005. The work of E.L. Gladin was also supported by an A.M. Raigorodskii scholarship in the field of numerical optimization methods. The work of A.V. Gasnikov was also partly supported by the Russian Foundation for Basic Research, project no. 18-29-03071 mk.
Presented by the member of Editorial Board: A. A. Lazarev

Received: 28.01.2021
Revised: 26.04.2021
Accepted: 30.06.2021
English version:
Automation and Remote Control, 2021, Volume 82, Issue 10, Pages 1679–1691
DOI: https://doi.org/10.1134/S0005117921100064
Bibliographic databases:
Document Type: Article
Language: Russian
Citation: E. L. Gladin, M. Alkousa, A. V. Gasnikov, “Solving convex min-min problems with smoothness and strong convexity in one group of variables and low dimension in the other”, Avtomat. i Telemekh., 2021, no. 10, 60–75; Autom. Remote Control, 82:10 (2021), 1679–1691
Citation in format AMSBIB
\Bibitem{GlaAlkGas21}
\by E.~L.~Gladin, M.~Alkousa, A.~V.~Gasnikov
\paper Solving convex min-min problems with smoothness and strong convexity in one group of variables and low dimension in the other
\jour Avtomat. i Telemekh.
\yr 2021
\issue 10
\pages 60--75
\mathnet{http://mi.mathnet.ru/at15800}
\crossref{https://doi.org/10.31857/S0005231021100068}
\transl
\jour Autom. Remote Control
\yr 2021
\vol 82
\issue 10
\pages 1679--1691
\crossref{https://doi.org/10.1134/S0005117921100064}
\isi{https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=Publons&SrcAuth=Publons_CEL&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=000721983400006}
\scopus{https://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85119653293}
Linking options:
  • https://www.mathnet.ru/eng/at15800
  • https://www.mathnet.ru/eng/at/y2021/i10/p60
  • 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:152
    Full-text PDF :1
    References:36
    First page:33
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024