An elementary approach to tight worst case complexity analysis of gradient based methods

This work presents a novel analysis that allows to achieve tight complexity bounds of gradient-based methods for convex optimization. We start by identifying some of the pitfalls rooted in the classical complexity analysis of the gradient descent method, and show how they can be remedied. Our method...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mathematical programming Jg. 201; H. 1-2; S. 63 - 96
Hauptverfasser: Teboulle, Marc, Vaisbourd, Yakov
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2023
Springer
Schlagworte:
ISSN:0025-5610, 1436-4646
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This work presents a novel analysis that allows to achieve tight complexity bounds of gradient-based methods for convex optimization. We start by identifying some of the pitfalls rooted in the classical complexity analysis of the gradient descent method, and show how they can be remedied. Our methodology hinges on elementary and direct arguments in the spirit of the classical analysis. It allows us to establish some new (and reproduce known) tight complexity results for several fundamental algorithms including, gradient descent, proximal point and proximal gradient methods which previously could be proven only through computer-assisted convergence proof arguments.
AbstractList This work presents a novel analysis that allows to achieve tight complexity bounds of gradient-based methods for convex optimization. We start by identifying some of the pitfalls rooted in the classical complexity analysis of the gradient descent method, and show how they can be remedied. Our methodology hinges on elementary and direct arguments in the spirit of the classical analysis. It allows us to establish some new (and reproduce known) tight complexity results for several fundamental algorithms including, gradient descent, proximal point and proximal gradient methods which previously could be proven only through computer-assisted convergence proof arguments.
Audience Academic
Author Teboulle, Marc
Vaisbourd, Yakov
Author_xml – sequence: 1
  givenname: Marc
  orcidid: 0000-0002-4228-131X
  surname: Teboulle
  fullname: Teboulle, Marc
  email: teboulle@tauex.tau.ac.il
  organization: School of Mathematical Sciences, Tel-Aviv University
– sequence: 2
  givenname: Yakov
  surname: Vaisbourd
  fullname: Vaisbourd, Yakov
  organization: Department of Mathematics and Statistics, McGill University
BookMark eNp9kM9KAzEQh4NUsK2-gKe8wNbJJpvNHkvxHxS8KHgLaTbZpuxuliSifXuj9eShzGFg-H3DzLdAs9GPBqFbAisCUN9FAgTqAsqyACKapoALNCeM8oJxxmdoDlBWRcUJXKFFjAcAIFSIOXpfj9j0ZjBjUuGI1TQFr_QeJ4-T6_YJf_oQE9YqGqz9MPXmy6WcG1V_jC5ib3EXVOsyj3c51OLBpL1v4zW6tKqP5uavL9Hbw_3r5qnYvjw-b9bbQlMKqeDW0rqmlVA7YQndMVWCtZoRahhXtjHMcis4MFI3Kp_fakF5lb9teANk19IlWp32dqo30o3Wp6B0rtYMTmdL1uX5uq4Ea4gomwyIE6CDjzEYK7VLKjk_ZtD1koD8USpPSmVWKn-VSsho-Q-dghuyt_MQPUExh8fOBHnwHyH7i-eob0Gpi3s
CitedBy_id crossref_primary_10_1287_moor_2024_0510
crossref_primary_10_1287_ijoo_2024_0057
crossref_primary_10_1287_moor_2024_0449
crossref_primary_10_1137_23M1588408
crossref_primary_10_1007_s10107_024_02143_7
crossref_primary_10_1365_s13291_023_00275_x
crossref_primary_10_1007_s10107_025_02258_5
Cites_doi 10.24033/bsmf.1625
10.1137/0716071
10.1137/080716542
10.1007/s10107-016-1009-3
10.1016/0022-247X(79)90234-8
10.1016/0041-5553(66)90114-5
10.1007/s10107-018-1284-2
10.1090/S0002-9904-1964-11178-2
10.1137/16M108104X
10.1137/1.9781611974997
10.1137/0329022
10.1007/s10957-020-01770-2
10.1007/s10107-013-0653-0
ContentType Journal Article
Copyright Springer-Verlag GmbH Germany, part of Springer Nature and Mathematical Optimization Society 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
COPYRIGHT 2023 Springer
Copyright_xml – notice: Springer-Verlag GmbH Germany, part of Springer Nature and Mathematical Optimization Society 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
– notice: COPYRIGHT 2023 Springer
DBID AAYXX
CITATION
DOI 10.1007/s10107-022-01899-0
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Mathematics
EISSN 1436-4646
EndPage 96
ExternalDocumentID A758491829
10_1007_s10107_022_01899_0
GrantInformation_xml – fundername: israel science foundation
  grantid: 2619-20
  funderid: http://dx.doi.org/10.13039/501100003977
GroupedDBID --K
--Z
-52
-5D
-5G
-BR
-EM
-Y2
-~C
-~X
.4S
.86
.DC
.VR
06D
0R~
0VY
199
1B1
1N0
1OL
1SB
203
28-
29M
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
3V.
4.4
406
408
409
40D
40E
5GY
5QI
5VS
67Z
6NX
6TJ
78A
7WY
88I
8AO
8FE
8FG
8FL
8TC
8UJ
8VB
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDBF
ABDZT
ABECU
ABFTV
ABHLI
ABHQN
ABJCF
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACGOD
ACHSB
ACHXU
ACIWK
ACKNC
ACMDZ
ACMLO
ACNCT
ACOKC
ACOMO
ACPIV
ACUHS
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMOZ
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFFNX
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHQJS
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
AKVCP
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
AZQEC
B-.
B0M
BA0
BAPOH
BBWZM
BDATZ
BENPR
BEZIV
BGLVJ
BGNMA
BPHCQ
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
DWQXO
EAD
EAP
EBA
EBLON
EBR
EBS
EBU
ECS
EDO
EIOEI
EJD
EMI
EMK
EPL
ESBYG
EST
ESX
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNUQQ
GNWQR
GQ6
GQ7
GQ8
GROUPED_ABI_INFORM_COMPLETE
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
H~9
I-F
I09
IAO
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K1G
K60
K6V
K6~
K7-
KDC
KOV
KOW
L6V
LAS
LLZTM
M0C
M0N
M2P
M4Y
M7S
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQ-
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
P19
P2P
P62
P9R
PF0
PQBIZ
PQBZA
PQQKQ
PROAC
PT4
PT5
PTHSS
Q2X
QOK
QOS
QWB
R4E
R89
R9I
RHV
RIG
RNI
RNS
ROL
RPX
RPZ
RSV
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCLPG
SDD
SDH
SDM
SHX
SISQX
SJYHP
SMT
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TH9
TN5
TSG
TSK
TSV
TUC
TUS
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WH7
WK8
XPP
YLTOR
Z45
Z5O
Z7R
Z7S
Z7X
Z7Y
Z7Z
Z81
Z83
Z86
Z88
Z8M
Z8N
Z8R
Z8T
Z8W
Z92
ZL0
ZMTXR
ZWQNP
~02
~8M
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
ADXHL
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
AMVHM
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
ID FETCH-LOGICAL-c330t-6ff377358ab8f13b4a20ffc413e46af9e4f6f8604179a610dc836510196901bd3
IEDL.DBID RSV
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867619800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0025-5610
IngestDate Sat Nov 29 10:30:39 EST 2025
Sat Nov 29 03:34:03 EST 2025
Tue Nov 18 22:31:20 EST 2025
Fri Feb 21 02:42:46 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1-2
Keywords Convex minimization
Gradient descent
68Q25
Performance estimation problem
Proximal schemes
90C30
Composite minimization
Global rate of convergence
90C25
90C60
Worst-case complexity analysis
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c330t-6ff377358ab8f13b4a20ffc413e46af9e4f6f8604179a610dc836510196901bd3
ORCID 0000-0002-4228-131X
PageCount 34
ParticipantIDs gale_infotracacademiconefile_A758491829
crossref_citationtrail_10_1007_s10107_022_01899_0
crossref_primary_10_1007_s10107_022_01899_0
springer_journals_10_1007_s10107_022_01899_0
PublicationCentury 2000
PublicationDate 20230900
2023-09-00
20230901
PublicationDateYYYYMMDD 2023-09-01
PublicationDate_xml – month: 9
  year: 2023
  text: 20230900
PublicationDecade 2020
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
PublicationSubtitle A Publication of the Mathematical Optimization Society
PublicationTitle Mathematical programming
PublicationTitleAbbrev Math. Program
PublicationYear 2023
Publisher Springer Berlin Heidelberg
Springer
Publisher_xml – name: Springer Berlin Heidelberg
– name: Springer
References CR4
Bertsekas (CR3) 2015
Goldstein (CR6) 1964; 70
Graham, Knuth, Patashnik (CR8) 1994
Taylor, Hendrickx, Glineur (CR16) 2017; 161
Beck, Teboulle (CR1) 2009; 2
Levitin, Polyak (CR10) 1966; 6
Lions, Mercier (CR11) 1979; 16
Moreau (CR13) 1965; 93
Teboulle (CR18) 2018; 170
Beck (CR2) 2017
Passty (CR14) 1979; 72
Drori, Teboulle (CR5) 2014; 145
Güler (CR7) 1991; 29
Sabach, Teboulle (CR15) 2019; 20
Taylor, Hendrickx, Glineur (CR17) 2017; 27
Kim, Fessler (CR9) 2021; 188
Martinet (CR12) 1970; 4
O Güler (1899_CR7) 1991; 29
R Graham (1899_CR8) 1994
J-J Moreau (1899_CR13) 1965; 93
A Beck (1899_CR2) 2017
A Beck (1899_CR1) 2009; 2
1899_CR4
B Martinet (1899_CR12) 1970; 4
DP Bertsekas (1899_CR3) 2015
D Kim (1899_CR9) 2021; 188
ES Levitin (1899_CR10) 1966; 6
GB Passty (1899_CR14) 1979; 72
M Teboulle (1899_CR18) 2018; 170
AA Goldstein (1899_CR6) 1964; 70
PL Lions (1899_CR11) 1979; 16
S Sabach (1899_CR15) 2019; 20
Y Drori (1899_CR5) 2014; 145
AB Taylor (1899_CR17) 2017; 27
AB Taylor (1899_CR16) 2017; 161
References_xml – year: 2017
  ident: CR2
  publication-title: First-Order Methods in Optimization
– year: 1994
  ident: CR8
  publication-title: Concrete Mathematics: A Foundation for Computer Science
– volume: 20
  start-page: 401
  year: 2019
  end-page: 436
  ident: CR15
  article-title: Lagrangian methods for composite optimization
  publication-title: Handb. Numer. Anal.
– volume: 2
  start-page: 183
  issue: 1
  year: 2009
  end-page: 202
  ident: CR1
  article-title: A fast iterative shrinkage-thresholding algorithm for linear inverse problems
  publication-title: SIAM J. Imag. Sci.
– year: 2015
  ident: CR3
  publication-title: Convex Optimization Algorithms
– ident: CR4
– volume: 70
  start-page: 709
  issue: 5
  year: 1964
  end-page: 710
  ident: CR6
  article-title: Convex programming in Hilbert space
  publication-title: B. Am. Math. Soc.
– volume: 188
  start-page: 192
  year: 2021
  end-page: 219
  ident: CR9
  article-title: Optimizing the efficiency of first-order methods for decreasing the gradient of smooth convex functions
  publication-title: J. Optim. Theory Appl.
– volume: 4
  start-page: 154
  year: 1970
  end-page: 158
  ident: CR12
  article-title: Régularisation d’inéquations variationnelles par approximations successives
  publication-title: Rev. Française Informatique. Recherche Opérationnelle
– volume: 93
  start-page: 273
  year: 1965
  end-page: 299
  ident: CR13
  article-title: Proximité et dualité dans un espace hilbertien
  publication-title: Bull. Soc. Math. France
– volume: 145
  start-page: 451
  issue: 1–2
  year: 2014
  end-page: 482
  ident: CR5
  article-title: Performance of first-order methods for smooth convex minimization: a novel approach
  publication-title: Math. Program. Ser. A
– volume: 161
  start-page: 307
  issue: 1–2
  year: 2017
  end-page: 345
  ident: CR16
  article-title: Smooth strongly convex interpolation and exact worst-case performance of first-order methods
  publication-title: Math. Program. Ser. A
– volume: 6
  start-page: 1
  issue: 5
  year: 1966
  end-page: 50
  ident: CR10
  article-title: Constrained minimization methods
  publication-title: USSR Comp. Math. Math. Phys.
– volume: 16
  start-page: 964
  issue: 6
  year: 1979
  end-page: 979
  ident: CR11
  article-title: Splitting algorithms for the sum of two nonlinear operators
  publication-title: SIAM J. Numer. Anal.
– volume: 27
  start-page: 1283
  issue: 3
  year: 2017
  end-page: 1313
  ident: CR17
  article-title: Exact worst-case performance of first-order methods for composite convex optimization
  publication-title: SIAM J. Optim.
– volume: 72
  start-page: 383
  issue: 2
  year: 1979
  end-page: 390
  ident: CR14
  article-title: Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
  publication-title: J. Math. Anal. Appl.
– volume: 170
  start-page: 67
  issue: 1
  year: 2018
  end-page: 96
  ident: CR18
  article-title: A simplified view of first order methods for optimization
  publication-title: Math. Program. Ser. B
– volume: 29
  start-page: 403
  issue: 2
  year: 1991
  end-page: 419
  ident: CR7
  article-title: On the convergence of the proximal point algorithm for convex minimization
  publication-title: SIAM J. Control. Optim.
– volume: 93
  start-page: 273
  year: 1965
  ident: 1899_CR13
  publication-title: Bull. Soc. Math. France
  doi: 10.24033/bsmf.1625
– ident: 1899_CR4
– volume-title: Concrete Mathematics: A Foundation for Computer Science
  year: 1994
  ident: 1899_CR8
– volume: 16
  start-page: 964
  issue: 6
  year: 1979
  ident: 1899_CR11
  publication-title: SIAM J. Numer. Anal.
  doi: 10.1137/0716071
– volume: 2
  start-page: 183
  issue: 1
  year: 2009
  ident: 1899_CR1
  publication-title: SIAM J. Imag. Sci.
  doi: 10.1137/080716542
– volume: 161
  start-page: 307
  issue: 1–2
  year: 2017
  ident: 1899_CR16
  publication-title: Math. Program. Ser. A
  doi: 10.1007/s10107-016-1009-3
– volume: 4
  start-page: 154
  year: 1970
  ident: 1899_CR12
  publication-title: Rev. Française Informatique. Recherche Opérationnelle
– volume-title: Convex Optimization Algorithms
  year: 2015
  ident: 1899_CR3
– volume: 72
  start-page: 383
  issue: 2
  year: 1979
  ident: 1899_CR14
  publication-title: J. Math. Anal. Appl.
  doi: 10.1016/0022-247X(79)90234-8
– volume: 6
  start-page: 1
  issue: 5
  year: 1966
  ident: 1899_CR10
  publication-title: USSR Comp. Math. Math. Phys.
  doi: 10.1016/0041-5553(66)90114-5
– volume: 20
  start-page: 401
  year: 2019
  ident: 1899_CR15
  publication-title: Handb. Numer. Anal.
– volume: 170
  start-page: 67
  issue: 1
  year: 2018
  ident: 1899_CR18
  publication-title: Math. Program. Ser. B
  doi: 10.1007/s10107-018-1284-2
– volume: 70
  start-page: 709
  issue: 5
  year: 1964
  ident: 1899_CR6
  publication-title: B. Am. Math. Soc.
  doi: 10.1090/S0002-9904-1964-11178-2
– volume: 27
  start-page: 1283
  issue: 3
  year: 2017
  ident: 1899_CR17
  publication-title: SIAM J. Optim.
  doi: 10.1137/16M108104X
– volume-title: First-Order Methods in Optimization
  year: 2017
  ident: 1899_CR2
  doi: 10.1137/1.9781611974997
– volume: 29
  start-page: 403
  issue: 2
  year: 1991
  ident: 1899_CR7
  publication-title: SIAM J. Control. Optim.
  doi: 10.1137/0329022
– volume: 188
  start-page: 192
  year: 2021
  ident: 1899_CR9
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/s10957-020-01770-2
– volume: 145
  start-page: 451
  issue: 1–2
  year: 2014
  ident: 1899_CR5
  publication-title: Math. Program. Ser. A
  doi: 10.1007/s10107-013-0653-0
SSID ssj0001388
Score 2.4304676
Snippet This work presents a novel analysis that allows to achieve tight complexity bounds of gradient-based methods for convex optimization. We start by identifying...
SourceID gale
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 63
SubjectTerms Calculus of Variations and Optimal Control; Optimization
Combinatorics
Full Length Paper
Mathematical and Computational Physics
Mathematical Methods in Physics
Mathematics
Mathematics and Statistics
Mathematics of Computing
Numerical Analysis
Theoretical
Title An elementary approach to tight worst case complexity analysis of gradient based methods
URI https://link.springer.com/article/10.1007/s10107-022-01899-0
Volume 201
WOSCitedRecordID wos000867619800002&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: PRVAVX
  databaseName: SpringerLink Contemporary
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1JS8QwFA46etCDuzhu5CB40EI7SdvkOIjixUFwYW4hzSKCtNLW7d-b16bjDMiAXgqFNoSXvC157_sQOtFWch4PbGB5AqdVXDk7GLsHZdRKY21KdUM2kY5GbDzmt74prOqq3bsrycZSTzW7RXCsNoBSAga984toKQYIJMjR7x4n9jcijHVErRAd-FaZ38eYcUedUZ69Em08zdX6_-a4gdZ8ZImH7VbYRAsm30KrU3iD7u1mAtJabaPxMMfGV4-XX7hDF8d1gWtI2fFH4UJDrJyfw03lufl0ITuWHsYEFxY_lU3FWI3BGWrc0lFXO-jh6vL-4jrwRAuBIiSsg8RakqYkZjJjNiIZlYPQWuX8m6GJtNxQm1iWhMBWJp1EtWIkAWXmQGeVabKLenmRmz2EnRanGhBlrM6oSjgDQDSdaRUnGZeG9FHUyVsoj0IOZBgv4gc_GWQonAxFI0MR9tHZ5J_XFoNj7tensIwCFNSNrKTvM3DzA6grMXQZEuUureJ9dN6tovCaW80ZeP9vnx-gFaCmb-vRDlGvLt_MEVpW7_VzVR43W_YbfQXkSw
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1JSwMxFH5oFdSDu1jXHAQPWmibdCY5FrFUbIvgQm8hk0UEaaUzbv_evGmmWpCCXgYGZkJ4yduS974P4MQ4JUSj7ipORHhaJbS3gw3_YJw5ZZ2LmcnJJuJej_f74iY0haVFtXtxJZlb6h_NbjU8VqtjKQHH3vl5WGAItI05-u3DxP7WKOcFUStGB6FV5vcxptxRYZSnr0RzT9Na-98c12E1RJakOd4KGzBnB5uw8gNv0L91JyCt6Rb0mwNiQ_X46JMU6OIkG5IMU3byPvShIdHez5G88tx--JCdqABjQoaOPI7yirGMoDM0ZExHnW7Dfevy7qJdCUQLFU1pNatEztE4pg2uEu5qNGGqXnVOe_9mWaScsMxFjkdVZCtTXqJGcxqhMguks0oM3YHSYDiwu0C8FscGEWWcSZiOBEdANJMY3YgSoSwtQ62Qt9QBhRzJMJ7lN34yylB6GcpchrJahrPJPy9jDI6ZX5_iMkpUUD-yVqHPwM8Poa5k02dITPi0SpThvFhFGTQ3nTHw3t8-P4al9l23IztXvet9WEaa-nFt2gGUstGrPYRF_ZY9paOjfPt-ATil5y8
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dSxwxEB-sitiHtmrFs1bzIPigh3eX3G7yeGgPRXuIX9xbyCaZIsiu3K2t_e_N7Md5B3JQ-rKwSzaEyUxmksz8fgD7Do1S3Q42UUV0WqVsWAe74SGkQOMRY-EKsol4MJDDobqaquIvst3rK8mypoFQmtL8-Mnh8VThW5uO2DqUViCpjv4DLInwiXT8-uZ-sha3uZQ1aStFClXZzPt9zLimeoGevR4tvE7_8_-P9wt8qiJO1itVZA0WfLoOH6dwCMPbzwl463gDhr2U-SqrfPSX1ajjLM9YTlt59icLISOzwf-xIiPdv4RQnpkK3oRlyH6NikyynJGTdKykqR5_hbv-j9uTs2ZFwNC0nLfyZoTI45h3pUkktnkiTKeFaIPf8yIyqLzACGXUIhYzE6TrrOQRGbkimqvE8U1YTLPUbwEL1h07QppBlwgbKUlAaS5xthslynjegHYte20rdHIiyXjUb7jKJEMdZKgLGepWAw4n_zyV2BxzWx_QlGoy3NCzNVX9QRgfQWDpXtg5CRW2W6oBR_WM6sqix3M63v635nuwcnXa15fng4tvsErs9WXK2g4s5qNn_x2W7e_8YTzaLTT5FXzR8BM
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=An+elementary+approach+to+tight+worst+case+complexity+analysis+of+gradient+based+methods&rft.jtitle=Mathematical+programming&rft.au=Teboulle%2C+Marc&rft.au=Vaisbourd%2C+Yakov&rft.date=2023-09-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=0025-5610&rft.eissn=1436-4646&rft.volume=201&rft.issue=1-2&rft.spage=63&rft.epage=96&rft_id=info:doi/10.1007%2Fs10107-022-01899-0&rft.externalDocID=10_1007_s10107_022_01899_0
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0025-5610&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0025-5610&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0025-5610&client=summon