Accelerated variance-reduced methods for saddle-point problems

We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non-bilinear objective functions augmented by simple composite regularizers for the primal and dual variables. For such problems, under the average-smoothness assumption, we propose acceler...

Full description

Saved in:
Bibliographic Details
Published in:EURO journal on computational optimization Vol. 10; p. 100048
Main Authors: Borodich, Ekaterina, Tominin, Vladislav, Tominin, Yaroslav, Kovalev, Dmitry, Gasnikov, Alexander, Dvurechensky, Pavel
Format: Journal Article
Language:English
Published: Elsevier Ltd 2022
Elsevier
Subjects:
ISSN:2192-4406
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non-bilinear objective functions augmented by simple composite regularizers for the primal and dual variables. For such problems, under the average-smoothness assumption, we propose accelerated stochastic variance-reduced algorithms with optimal up to logarithmic factors complexity bounds. In particular, we consider strongly-convex-strongly-concave, convex-strongly-concave, and convex-concave objectives. To the best of our knowledge, these are the first nearly-optimal algorithms for this setting. •Optimal accelerated stochastic variance-reduced algorithm for composite saddle-point problems.•Saddle-point problems with different strongly-convex and strongly-concave parameters.•Upper bounds for composite saddle-point problems with a finite sum structure.•Achieving the lower bounds for composite saddle-point problems with finite sum structure up to logarithmic factor.
AbstractList We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non-bilinear objective functions augmented by simple composite regularizers for the primal and dual variables. For such problems, under the average-smoothness assumption, we propose accelerated stochastic variance-reduced algorithms with optimal up to logarithmic factors complexity bounds. In particular, we consider strongly-convex-strongly-concave, convex-strongly-concave, and convex-concave objectives. To the best of our knowledge, these are the first nearly-optimal algorithms for this setting. •Optimal accelerated stochastic variance-reduced algorithm for composite saddle-point problems.•Saddle-point problems with different strongly-convex and strongly-concave parameters.•Upper bounds for composite saddle-point problems with a finite sum structure.•Achieving the lower bounds for composite saddle-point problems with finite sum structure up to logarithmic factor.
We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non-bilinear objective functions augmented by simple composite regularizers for the primal and dual variables. For such problems, under the average-smoothness assumption, we propose accelerated stochastic variance-reduced algorithms with optimal up to logarithmic factors complexity bounds. In particular, we consider strongly-convex-strongly-concave, convex-strongly-concave, and convex-concave objectives. To the best of our knowledge, these are the first nearly-optimal algorithms for this setting.
ArticleNumber 100048
Author Kovalev, Dmitry
Dvurechensky, Pavel
Borodich, Ekaterina
Tominin, Vladislav
Tominin, Yaroslav
Gasnikov, Alexander
Author_xml – sequence: 1
  givenname: Ekaterina
  orcidid: 0000-0003-3339-6550
  surname: Borodich
  fullname: Borodich, Ekaterina
  email: borodich.ed@phystech.edu
  organization: Moscow Institute of Physics and Technology, Moscow, Russia
– sequence: 2
  givenname: Vladislav
  surname: Tominin
  fullname: Tominin, Vladislav
  email: tominin.vd@phystech.edu
  organization: Moscow Institute of Physics and Technology, Moscow, Russia
– sequence: 3
  givenname: Yaroslav
  surname: Tominin
  fullname: Tominin, Yaroslav
  email: tominin.yad@phystech.edu
  organization: Moscow Institute of Physics and Technology, Moscow, Russia
– sequence: 4
  givenname: Dmitry
  surname: Kovalev
  fullname: Kovalev, Dmitry
  email: dmitry.kovalev@kaust.edu.sa
  organization: King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
– sequence: 5
  givenname: Alexander
  surname: Gasnikov
  fullname: Gasnikov, Alexander
  email: gasnikov.av@mipt.ru
  organization: Moscow Institute of Physics and Technology, Moscow, Russia
– sequence: 6
  givenname: Pavel
  orcidid: 0000-0003-1201-2343
  surname: Dvurechensky
  fullname: Dvurechensky, Pavel
  email: pavel.dvurechensky@wias-berlin.de
  organization: Weierstrass Institute for Applied Analysis and Stochastics, Berlin, Germany
BookMark eNp9kE1LAzEQhnOoYK39A572D2zN5-4GRCjFj0LBi55DdjKrWbZNSdaC_97UFY-eBh7mfZl5rsjsEA5IyA2jK0ZZdduvsIew4pTzDCiVzYzMOdO8lJJWl2SZUp8xU7SmQs3J_RoAB4x2RFecbPT2AFhGdJ-QwR7Hj-BS0YVYJOvcgOUx-MNYHGNoB9yna3LR2SHh8ncuyNvjw-vmudy9PG03610JomJjKTkid84yC7YGJmznGtco4CC7igohKXWqaZu8o4QEJiWgQsosqzXWHYgF2U69LtjeHKPf2_hlgvXmB4T4bmwcPQxosNWu1lY5XdVSaNUorpVrdUMZKmir3MWnLoghpYjdXx-j5izR9OYs0ZwlmkliDt1NIcxfnjxGk8BjduV8RBjzGf6_-DcKTn4n
Cites_doi 10.1007/s10957-022-02038-7
10.1111/j.1467-9868.2005.00503.x
10.1080/10556788.2021.1924714
10.1007/s10957-022-02062-7
10.1137/S1052623403422285
10.1007/s10851-010-0251-1
10.2307/1907266
10.1134/S0965542520110020
10.1007/s10107-006-0034-z
10.1134/S096554252101005X
10.1287/moor.2021.1175
10.1007/s10957-015-0771-3
10.1561/2400000003
10.1007/s10107-017-1161-4
10.24033/bsmf.1625
10.1137/S1052623403425629
10.1007/s10107-004-0552-5
ContentType Journal Article
Copyright 2022 The Author(s)
Copyright_xml – notice: 2022 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.ejco.2022.100048
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals (DOAJ)
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID oai_doaj_org_article_eb9d79a5d967439585295db9801e5cb6
10_1016_j_ejco_2022_100048
S2192440622000247
GroupedDBID -EM
0R~
0SF
0VY
203
30V
3V.
4.4
408
409
6I.
7WY
8FE
8FG
8FL
96X
AAEDW
AAFTH
AAIAL
AAJKR
AALRI
AARHV
AARTL
AATVU
AAWCG
AAXUO
AAYIU
AAYQN
AAYTO
AAZMS
ABBXA
ABDZT
ABFTV
ABJNI
ABJOX
ABKCH
ABQBU
ABTEG
ABTMW
ABUWG
ABXPI
ACGFS
ACIPQ
ACKNC
ACMLO
ACOKC
ADHHG
ADHIR
ADINQ
ADKPE
ADRFC
ADURQ
ADVLN
ADYFF
ADZKW
AEBTG
AEGNC
AEJHL
AEJRE
AEOHA
AEPYU
AETCA
AEXQZ
AEXYK
AFBBN
AFKRA
AFLOW
AFWTZ
AFZKB
AGAYW
AGDGC
AGQMX
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AILAN
AITGF
AITUG
AJBLW
AJRNO
AJZVZ
AKLTO
AKRWK
ALFXC
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMRAJ
AMYQR
ANMIH
ARAPS
ASPBG
AUKKA
AVWKF
AVXWI
AXJJW
AXYYD
AYQZM
AZFZN
AZQEC
BAPOH
BENPR
BEZIV
BGLVJ
BGNMA
BPHCQ
CCPQU
CSCUP
DWQXO
EBS
EIOEI
EJD
ESBYG
FDB
FEDTE
FERAY
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FYJPI
GGRSB
GJIRD
GNUQQ
GROUPED_DOAJ
HCIFZ
HF~
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I0C
IXD
J-C
JBSCW
JCJTX
K60
K6V
K6~
K7-
KOV
M0C
M0N
M4Y
NB0
NQJWS
NU0
O9-
O93
O9G
O9J
OK1
P62
PQBIZ
PQBZA
PQQKQ
PROAC
RLLFE
ROL
RSV
SHX
SISQX
SNX
SOJ
SPISZ
STPWE
TSG
UG4
UOJIU
UTJUX
UZXMN
VFIZW
W48
ZMTXR
AAYWO
AAYXX
ABFSG
ACSTC
ACVFH
ADCNI
AEUPX
AEZWR
AFFHD
AFHIU
AFPUW
AHWEU
AIGII
AIXLP
AKBMS
AKYEP
APXCP
CITATION
PHGZM
PHGZT
PQGLB
ID FETCH-LOGICAL-c361t-42ee2dda1aca7c13afd8d85c2c4f6033400d58b82dd534c144ce5e01a179e7fc3
IEDL.DBID DOA
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000876421600004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2192-4406
IngestDate Fri Oct 03 12:50:51 EDT 2025
Wed Nov 05 20:59:22 EST 2025
Mon Sep 30 11:37:07 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Minimax optimization
Composite optimization
Saddle-point problem
Accelerated algorithms
Stochastic variance-reduced algorithms
Language English
License This is an open access article under the CC BY license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c361t-42ee2dda1aca7c13afd8d85c2c4f6033400d58b82dd534c144ce5e01a179e7fc3
ORCID 0000-0003-3339-6550
0000-0003-1201-2343
OpenAccessLink https://doaj.org/article/eb9d79a5d967439585295db9801e5cb6
ParticipantIDs doaj_primary_oai_doaj_org_article_eb9d79a5d967439585295db9801e5cb6
crossref_primary_10_1016_j_ejco_2022_100048
elsevier_sciencedirect_doi_10_1016_j_ejco_2022_100048
PublicationCentury 2000
PublicationDate 2022
2022-00-00
2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – year: 2022
  text: 2022
PublicationDecade 2020
PublicationTitle EURO journal on computational optimization
PublicationYear 2022
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Shalev-Shwartz, Zhang (br0360) 2014; vol. 32
Zou, Hastie (br0440) 2005; 67
Chambolle, Pock (br0040) 2011; 40
Chen, Wang, Ge (br0050) 2018
Lu, Singh, Chen, Chen, Hong (br0230) 2018
Nesterov (br0300) 2005; 16
Alkousa, Gasnikov, Dvinskikh, Kovalev, Stonyakin (br0020) 2020; 60
Chen, Lan, Ouyang (br0060) 2017; 165
Lin, Mairal, Harchaoui (br0200) 2015
Woodworth, Srebro (br0410) 2016; vol. 29
Han, Xie, Zhang (br0120) 2021
Nesterov (br0320) 2007; 109
Carmon, Jin, Sidford, Tian (br0030) 2019
Gasnikov (br0110) 2015; 27
Nesterov (br0310) 2005; 103
Lin, Mairal, Harchaoui (br0210) 2018
Parikh, Boyd (br0350) 2014; 1
Zhao (br0430) 2022; 47
Gasnikov, Dvinskikh, Dvurechensky, Kamzolov, Matyukhin, Pasechnyuk, Tupitsa, Chernov (br0100) 2021; 61
Palaniappan, Bach (br0340) 2016; vol. 29
Stonyakin, Tyurin, Gasnikov, Dvurechensky, Agafonov, Dvinskikh, Alkousa, Pasechnyuk, Artamonov, Piskunova (br0380) 2021; 36
Gasnikov, Dvurechensky, Nesterov (br0090) 2016; 8
Ibrahim, Azizian, Gidel, Mitliagkas (br0140) 2020
Tominin, Tominin, Borodich, Kovalev, Gasnikov, Dvurechensky (br0400) 2021
Gasnikov (br0080) 2016
Song, Wright, Diakonikolas (br0370) 2021; vol. 139
Lin, Jin, Jordan (br0220) 2020; 125
Johnson, Zhang (br0170) 2013; vol. 26
Xie, Han, Zhang (br0420) 2021
Alacaoglu, Malitsky (br0010) 2022; vol. 178
Stonyakin, Gasnikov, Dvurechensky, Titov, Alkousa (br0390) 2022; 194
Nash (br0260) 1950
Dvurechensky, Nesterov, Spokoiny (br0070) 2015; 166
Morgenstern, Von Neumann (br0250) 1953
Hien, Zhao, Haskell (br0130) 2020
Kovalev, Gasnikov, Richtárik (br0180) 2021
Nesterov (br0290) 2004
Nemirovski (br0270) 2004; 15
Isaacs (br0150) 1999
Ivanova, Dvurechensky, Vorontsova, Pasechnyuk, Gasnikov, Dvinskikh, Tyurin (br0160) 2022; 193
Nesterov, Scrimali (br0330) 2011
Moreau (br0240) 1965; 93
Nemirovsky, Yudin (br0280) 1983
Lan (br0190) 2020
Chen (10.1016/j.ejco.2022.100048_br0050) 2018
Chen (10.1016/j.ejco.2022.100048_br0060) 2017; 165
Johnson (10.1016/j.ejco.2022.100048_br0170) 2013; vol. 26
Gasnikov (10.1016/j.ejco.2022.100048_br0110) 2015; 27
Nesterov (10.1016/j.ejco.2022.100048_br0300) 2005; 16
Woodworth (10.1016/j.ejco.2022.100048_br0410) 2016; vol. 29
Lin (10.1016/j.ejco.2022.100048_br0210) 2018
Hien (10.1016/j.ejco.2022.100048_br0130)
Parikh (10.1016/j.ejco.2022.100048_br0350) 2014; 1
Lin (10.1016/j.ejco.2022.100048_br0220) 2020; 125
Shalev-Shwartz (10.1016/j.ejco.2022.100048_br0360) 2014; vol. 32
Lin (10.1016/j.ejco.2022.100048_br0200) 2015
Stonyakin (10.1016/j.ejco.2022.100048_br0380) 2021; 36
Morgenstern (10.1016/j.ejco.2022.100048_br0250) 1953
Tominin (10.1016/j.ejco.2022.100048_br0400)
Zou (10.1016/j.ejco.2022.100048_br0440) 2005; 67
Isaacs (10.1016/j.ejco.2022.100048_br0150) 1999
Gasnikov (10.1016/j.ejco.2022.100048_br0100) 2021; 61
Nesterov (10.1016/j.ejco.2022.100048_br0320) 2007; 109
Gasnikov (10.1016/j.ejco.2022.100048_br0090) 2016; 8
Nesterov (10.1016/j.ejco.2022.100048_br0330)
Kovalev (10.1016/j.ejco.2022.100048_br0180)
Dvurechensky (10.1016/j.ejco.2022.100048_br0070) 2015; 166
Han (10.1016/j.ejco.2022.100048_br0120)
Nesterov (10.1016/j.ejco.2022.100048_br0310) 2005; 103
Song (10.1016/j.ejco.2022.100048_br0370) 2021; vol. 139
Chambolle (10.1016/j.ejco.2022.100048_br0040) 2011; 40
Ibrahim (10.1016/j.ejco.2022.100048_br0140) 2020
Moreau (10.1016/j.ejco.2022.100048_br0240) 1965; 93
Lu (10.1016/j.ejco.2022.100048_br0230) 2018
Alkousa (10.1016/j.ejco.2022.100048_br0020) 2020; 60
Alacaoglu (10.1016/j.ejco.2022.100048_br0010) 2022; vol. 178
Nemirovsky (10.1016/j.ejco.2022.100048_br0280) 1983
Lan (10.1016/j.ejco.2022.100048_br0190) 2020
Nash (10.1016/j.ejco.2022.100048_br0260) 1950
Zhao (10.1016/j.ejco.2022.100048_br0430) 2022; 47
Nemirovski (10.1016/j.ejco.2022.100048_br0270) 2004; 15
Nesterov (10.1016/j.ejco.2022.100048_br0290) 2004
Gasnikov (10.1016/j.ejco.2022.100048_br0080)
Ivanova (10.1016/j.ejco.2022.100048_br0160) 2022; 193
Xie (10.1016/j.ejco.2022.100048_br0420)
Stonyakin (10.1016/j.ejco.2022.100048_br0390) 2022; 194
Carmon (10.1016/j.ejco.2022.100048_br0030) 2019
Palaniappan (10.1016/j.ejco.2022.100048_br0340) 2016; vol. 29
References_xml – year: 2018
  ident: br0050
  article-title: Training generative adversarial networks via primal-dual subgradient methods: a lagrangian perspective on gan
  publication-title: Proceedings of the 6th International Conference on Learning Representations
– year: 2021
  ident: br0180
  article-title: Accelerated primal-dual gradient method for smooth and convex-concave saddle-point problems with bilinear coupling
– year: 1953
  ident: br0250
  article-title: Theory of Games and Economic Behavior
– volume: 40
  start-page: 120
  year: 2011
  end-page: 145
  ident: br0040
  article-title: A first-order primal-dual algorithm for convex problems with applications to imaging
  publication-title: J. Math. Imaging Vis.
– start-page: 11381
  year: 2019
  end-page: 11392
  ident: br0030
  article-title: Variance reduction for matrix games
  publication-title: Advances in Neural Information Processing Systems
– year: 2021
  ident: br0120
  article-title: Lower complexity bounds of finite-sum optimization problems: the results and construction
– year: 1999
  ident: br0150
  article-title: Differential Games: a Mathematical Theory with Applications to Warfare and Pursuit, Control and Optimization
– volume: 165
  start-page: 113
  year: 2017
  end-page: 149
  ident: br0060
  article-title: Accelerated schemes for a class of variational inequalities
  publication-title: Math. Program.
– volume: 93
  start-page: 273
  year: 1965
  end-page: 299
  ident: br0240
  article-title: Proximité et dualité dans un espace hilbertien
  publication-title: Bull. Soc. Math. Fr.
– volume: 8
  start-page: 41
  year: 2016
  end-page: 91
  ident: br0090
  article-title: Stochastic gradient methods with inexact oracle
  publication-title: Proc. Moscow Inst. Phys. Technol.
– year: 2020
  ident: br0130
  article-title: An inexact primal-dual smoothing framework for large-scale non-bilinear saddle point problems
– year: 2021
  ident: br0420
  article-title: Dippa: an improved method for bilinear saddle point problems
– volume: 47
  start-page: 1443
  year: 2022
  end-page: 1473
  ident: br0430
  article-title: Accelerated stochastic algorithms for convex-concave saddle-point problems
  publication-title: Math. Oper. Res.
– year: 2018
  ident: br0230
  article-title: Understand the dynamics of gans via primal-dual optimization
  publication-title: Proceedings of the 7th International Conference on Learning Representations
– volume: 166
  start-page: 23
  year: 2015
  end-page: 51
  ident: br0070
  article-title: Primal-dual methods for solving infinite-dimensional games
  publication-title: J. Optim. Theory Appl.
– year: 2021
  ident: br0400
  article-title: On accelerated methods for saddle-point problems with composite structure
– volume: 16
  start-page: 235
  year: 2005
  end-page: 249
  ident: br0300
  article-title: Excessive gap technique in nonsmooth convex minimization
  publication-title: SIAM J. Optim.
– volume: vol. 139
  start-page: 9824
  year: 2021
  end-page: 9834
  ident: br0370
  article-title: Variance reduction via primal-dual accelerated dual averaging for nonsmooth convex finite-sums
  publication-title: Proceedings of the 38th International Conference on Machine Learning
– year: 1983
  ident: br0280
  article-title: Problem Complexity and Method Efficiency in Optimization
– volume: 103
  start-page: 127
  year: 2005
  end-page: 152
  ident: br0310
  article-title: Smooth minimization of non-smooth functions
  publication-title: Math. Program.
– year: 2020
  ident: br0190
  article-title: First-Order and Stochastic Optimization Methods for Machine Learning
– volume: 27
  start-page: 121
  year: 2015
  end-page: 136
  ident: br0110
  article-title: Reduction of searching competetive equillibrium to the minimax problem in application to different network problems
  publication-title: Mat. Model.
– volume: 125
  start-page: 2738
  year: 2020
  end-page: 2779
  ident: br0220
  article-title: Near-optimal algorithms for minimax optimization
  publication-title: Proceedings of Thirty Third Conference on Learning Theory
– volume: 193
  start-page: 462
  year: 2022
  end-page: 490
  ident: br0160
  article-title: Oracle complexity separation in convex optimization
  publication-title: J. Optim. Theory Appl.
– start-page: 155
  year: 1950
  end-page: 162
  ident: br0260
  article-title: The bargaining problem
  publication-title: Econometrica
– volume: 194
  start-page: 988
  year: 2022
  end-page: 1013
  ident: br0390
  article-title: Generalized mirror prox algorithm for monotone variational inequalities: universality and inexact oracle
  publication-title: J. Optim. Theory Appl.
– volume: 109
  start-page: 319
  year: 2007
  end-page: 344
  ident: br0320
  article-title: Dual extrapolation and its applications to solving variational inequalities and related problems
  publication-title: Math. Program.
– volume: vol. 29
  year: 2016
  ident: br0410
  article-title: Tight complexity bounds for optimizing composite objectives
  publication-title: Advances in Neural Information Processing Systems
– volume: vol. 178
  start-page: 778
  year: 2022
  end-page: 816
  ident: br0010
  article-title: Stochastic variance reduction for variational inequality methods
  publication-title: Proceedings of Thirty Fifth Conference on Learning Theory
– year: 2016
  ident: br0080
  article-title: Searching equillibriums in large transport networks
– volume: 15
  start-page: 229
  year: 2004
  end-page: 251
  ident: br0270
  article-title: Prox-method with rate of convergence
  publication-title: SIAM J. Optim.
– year: 2018
  ident: br0210
  article-title: Catalyst acceleration for first-order convex optimization: from theory to practice
  publication-title: J. Mach. Learn. Res.
– year: 2011
  ident: br0330
  article-title: Solving strongly monotone variational and quasi-variational inequalities
– start-page: 4583
  year: 2020
  end-page: 4593
  ident: br0140
  article-title: Linear lower bounds and conditioning of differentiable games
  publication-title: International Conference on Machine Learning
– volume: vol. 26
  year: 2013
  ident: br0170
  article-title: Accelerating stochastic gradient descent using predictive variance reduction
  publication-title: Advances in Neural Information Processing Systems
– volume: vol. 32
  start-page: 64
  year: 2014
  end-page: 72
  ident: br0360
  article-title: Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
  publication-title: Proceedings of the 31st International Conference on Machine Learning
– volume: 1
  start-page: 127
  year: 2014
  end-page: 239
  ident: br0350
  article-title: Proximal algorithms
  publication-title: Found. Trends Optim.
– volume: 36
  start-page: 1155
  year: 2021
  end-page: 1201
  ident: br0380
  article-title: Inexact model: a framework for optimization and variational inequalities
  publication-title: Optim. Methods Softw.
– volume: 60
  start-page: 1787
  year: 2020
  end-page: 1809
  ident: br0020
  article-title: Accelerated methods for saddle-point problem
  publication-title: Comput. Math. Math. Phys.
– year: 2004
  ident: br0290
  article-title: Introductory Lectures on Convex Optimization: A Basic Course
– volume: vol. 29
  year: 2016
  ident: br0340
  article-title: Stochastic variance reduction methods for saddle-point problems
  publication-title: Advances in Neural Information Processing Systems
– year: 2015
  ident: br0200
  article-title: A universal catalyst for first-order optimization
  publication-title: Proceedings of
– volume: 67
  start-page: 301
  year: 2005
  end-page: 320
  ident: br0440
  article-title: Regularization and variable selection via the elastic net
  publication-title: J. R. Stat. Soc., Ser. B
– volume: 61
  start-page: 17
  year: 2021
  end-page: 28
  ident: br0100
  article-title: Accelerated meta-algorithm for convex optimization problems
  publication-title: Comput. Math. Math. Phys.
– volume: 193
  start-page: 462
  issue: 1
  year: 2022
  ident: 10.1016/j.ejco.2022.100048_br0160
  article-title: Oracle complexity separation in convex optimization
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/s10957-022-02038-7
– volume: 67
  start-page: 301
  issue: 2
  year: 2005
  ident: 10.1016/j.ejco.2022.100048_br0440
  article-title: Regularization and variable selection via the elastic net
  publication-title: J. R. Stat. Soc., Ser. B
  doi: 10.1111/j.1467-9868.2005.00503.x
– volume: 36
  start-page: 1155
  issue: 6
  year: 2021
  ident: 10.1016/j.ejco.2022.100048_br0380
  article-title: Inexact model: a framework for optimization and variational inequalities
  publication-title: Optim. Methods Softw.
  doi: 10.1080/10556788.2021.1924714
– volume: 194
  start-page: 988
  issue: 3
  year: 2022
  ident: 10.1016/j.ejco.2022.100048_br0390
  article-title: Generalized mirror prox algorithm for monotone variational inequalities: universality and inexact oracle
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/s10957-022-02062-7
– volume: 16
  start-page: 235
  issue: 1
  year: 2005
  ident: 10.1016/j.ejco.2022.100048_br0300
  article-title: Excessive gap technique in nonsmooth convex minimization
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623403422285
– volume: 27
  start-page: 121
  issue: 12
  year: 2015
  ident: 10.1016/j.ejco.2022.100048_br0110
  article-title: Reduction of searching competetive equillibrium to the minimax problem in application to different network problems
  publication-title: Mat. Model.
– volume: 40
  start-page: 120
  issue: 1
  year: 2011
  ident: 10.1016/j.ejco.2022.100048_br0040
  article-title: A first-order primal-dual algorithm for convex problems with applications to imaging
  publication-title: J. Math. Imaging Vis.
  doi: 10.1007/s10851-010-0251-1
– volume: 8
  start-page: 41
  issue: 1
  year: 2016
  ident: 10.1016/j.ejco.2022.100048_br0090
  article-title: Stochastic gradient methods with inexact oracle
  publication-title: Proc. Moscow Inst. Phys. Technol.
– year: 1999
  ident: 10.1016/j.ejco.2022.100048_br0150
– year: 2018
  ident: 10.1016/j.ejco.2022.100048_br0230
  article-title: Understand the dynamics of gans via primal-dual optimization
– start-page: 155
  year: 1950
  ident: 10.1016/j.ejco.2022.100048_br0260
  article-title: The bargaining problem
  publication-title: Econometrica
  doi: 10.2307/1907266
– volume: 60
  start-page: 1787
  issue: 11
  year: 2020
  ident: 10.1016/j.ejco.2022.100048_br0020
  article-title: Accelerated methods for saddle-point problem
  publication-title: Comput. Math. Math. Phys.
  doi: 10.1134/S0965542520110020
– volume: 109
  start-page: 319
  issue: 2–3
  year: 2007
  ident: 10.1016/j.ejco.2022.100048_br0320
  article-title: Dual extrapolation and its applications to solving variational inequalities and related problems
  publication-title: Math. Program.
  doi: 10.1007/s10107-006-0034-z
– volume: vol. 178
  start-page: 778
  year: 2022
  ident: 10.1016/j.ejco.2022.100048_br0010
  article-title: Stochastic variance reduction for variational inequality methods
– year: 2018
  ident: 10.1016/j.ejco.2022.100048_br0050
  article-title: Training generative adversarial networks via primal-dual subgradient methods: a lagrangian perspective on gan
– volume: vol. 32
  start-page: 64
  year: 2014
  ident: 10.1016/j.ejco.2022.100048_br0360
  article-title: Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
– ident: 10.1016/j.ejco.2022.100048_br0080
– volume: vol. 29
  year: 2016
  ident: 10.1016/j.ejco.2022.100048_br0340
  article-title: Stochastic variance reduction methods for saddle-point problems
– year: 2020
  ident: 10.1016/j.ejco.2022.100048_br0190
– ident: 10.1016/j.ejco.2022.100048_br0120
– volume: 61
  start-page: 17
  issue: 1
  year: 2021
  ident: 10.1016/j.ejco.2022.100048_br0100
  article-title: Accelerated meta-algorithm for convex optimization problems
  publication-title: Comput. Math. Math. Phys.
  doi: 10.1134/S096554252101005X
– year: 2004
  ident: 10.1016/j.ejco.2022.100048_br0290
– year: 1983
  ident: 10.1016/j.ejco.2022.100048_br0280
– ident: 10.1016/j.ejco.2022.100048_br0180
– year: 1953
  ident: 10.1016/j.ejco.2022.100048_br0250
– year: 2018
  ident: 10.1016/j.ejco.2022.100048_br0210
  article-title: Catalyst acceleration for first-order convex optimization: from theory to practice
  publication-title: J. Mach. Learn. Res.
– volume: 47
  start-page: 1443
  issue: 2
  year: 2022
  ident: 10.1016/j.ejco.2022.100048_br0430
  article-title: Accelerated stochastic algorithms for convex-concave saddle-point problems
  publication-title: Math. Oper. Res.
  doi: 10.1287/moor.2021.1175
– volume: 166
  start-page: 23
  issue: 1
  year: 2015
  ident: 10.1016/j.ejco.2022.100048_br0070
  article-title: Primal-dual methods for solving infinite-dimensional games
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/s10957-015-0771-3
– volume: 1
  start-page: 127
  issue: 3
  year: 2014
  ident: 10.1016/j.ejco.2022.100048_br0350
  article-title: Proximal algorithms
  publication-title: Found. Trends Optim.
  doi: 10.1561/2400000003
– ident: 10.1016/j.ejco.2022.100048_br0400
– start-page: 11381
  year: 2019
  ident: 10.1016/j.ejco.2022.100048_br0030
  article-title: Variance reduction for matrix games
– year: 2015
  ident: 10.1016/j.ejco.2022.100048_br0200
  article-title: A universal catalyst for first-order optimization
– volume: vol. 29
  year: 2016
  ident: 10.1016/j.ejco.2022.100048_br0410
  article-title: Tight complexity bounds for optimizing composite objectives
– volume: 165
  start-page: 113
  issue: 1
  year: 2017
  ident: 10.1016/j.ejco.2022.100048_br0060
  article-title: Accelerated schemes for a class of variational inequalities
  publication-title: Math. Program.
  doi: 10.1007/s10107-017-1161-4
– volume: vol. 139
  start-page: 9824
  year: 2021
  ident: 10.1016/j.ejco.2022.100048_br0370
  article-title: Variance reduction via primal-dual accelerated dual averaging for nonsmooth convex finite-sums
– volume: 93
  start-page: 273
  year: 1965
  ident: 10.1016/j.ejco.2022.100048_br0240
  article-title: Proximité et dualité dans un espace hilbertien
  publication-title: Bull. Soc. Math. Fr.
  doi: 10.24033/bsmf.1625
– volume: 15
  start-page: 229
  issue: 1
  year: 2004
  ident: 10.1016/j.ejco.2022.100048_br0270
  article-title: Prox-method with rate of convergence o(1/t) for variational inequalities with Lipschitz continuous monotone operators and smooth convex-concave saddle point problems
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623403425629
– start-page: 4583
  year: 2020
  ident: 10.1016/j.ejco.2022.100048_br0140
  article-title: Linear lower bounds and conditioning of differentiable games
– ident: 10.1016/j.ejco.2022.100048_br0330
– volume: vol. 26
  year: 2013
  ident: 10.1016/j.ejco.2022.100048_br0170
  article-title: Accelerating stochastic gradient descent using predictive variance reduction
– volume: 125
  start-page: 2738
  year: 2020
  ident: 10.1016/j.ejco.2022.100048_br0220
  article-title: Near-optimal algorithms for minimax optimization
  publication-title: Proc. Mach. Learn. Res.
– volume: 103
  start-page: 127
  issue: 1
  year: 2005
  ident: 10.1016/j.ejco.2022.100048_br0310
  article-title: Smooth minimization of non-smooth functions
  publication-title: Math. Program.
  doi: 10.1007/s10107-004-0552-5
– ident: 10.1016/j.ejco.2022.100048_br0420
– ident: 10.1016/j.ejco.2022.100048_br0130
SSID ssj0001507035
Score 2.1823652
Snippet We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non-bilinear objective functions augmented by...
SourceID doaj
crossref
elsevier
SourceType Open Website
Index Database
Publisher
StartPage 100048
SubjectTerms Accelerated algorithms
Composite optimization
Minimax optimization
Saddle-point problem
Stochastic variance-reduced algorithms
Title Accelerated variance-reduced methods for saddle-point problems
URI https://dx.doi.org/10.1016/j.ejco.2022.100048
https://doaj.org/article/eb9d79a5d967439585295db9801e5cb6
Volume 10
WOSCitedRecordID wos000876421600004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Directory of Open Access Journals (DOAJ)
  issn: 2192-4406
  databaseCode: DOA
  dateStart: 20130101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: false
  ssIdentifier: ssj0001507035
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NS8QwEA2yeNCD-InrFz14k2CbNm1yEVZx8SCLB4W9hXSSwu6hK9u6v9-Zpis96cVrCEl5k_TNhJk3jN0iBVU5hjvciiTnGRIsV3nsOFiZQOEzlQYR19diNlPzuX4btPqinLAgDxyAu_eldoW20mlKl9fo3QotXanxz-ollJ3YdlzoQTAV6oPpKFP-It5IwTOkrb5iJiR3-SVQ5Z8QlCUQU_OfASt14v0DchoQzvSQHfSeYjQJX3jEdnx9zPYH-oEn7GECgLRBag8u2mDUSybka1JjxYHQHLqJ0C2NGkvvEPxztajbqG8i05yyj-nz-9ML7xsicEjzpOWZ8F44ZxMLtoAktZVTTkkQkCHgaYr30UlVKpwj0wwwVgIvfZxYvHW-qCA9Y6N6VftzFokqVhUIJC6nMuk1OmJl4X1ekgNYWTlmd1tAzGfQvTDbhLClIfgMwWcCfGP2SJj9zCTN6m4ALWl6S5q_LDlmcou46ek_0Doutfhl84v_2PyS7dGS4XHlio3a9Ze_ZruwaRfN-qY7XN9-Hc_X
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Accelerated+variance-reduced+methods+for+saddle-point+problems&rft.jtitle=EURO+journal+on+computational+optimization&rft.au=Borodich%2C+Ekaterina&rft.au=Tominin%2C+Vladislav&rft.au=Tominin%2C+Yaroslav&rft.au=Kovalev%2C+Dmitry&rft.date=2022&rft.issn=2192-4406&rft.volume=10&rft.spage=100048&rft_id=info:doi/10.1016%2Fj.ejco.2022.100048&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ejco_2022_100048
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2192-4406&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2192-4406&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2192-4406&client=summon