A conditional gradient algorithm for distributed online optimization in networks

This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local estimation and communication, without any central coordinator. An online distributed conditional gradient algorithm based on the conditional...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IET control theory & applications Ročník 15; číslo 4; s. 570 - 579
Hlavní autoři: Shen, Xiuyu, Li, Dequan, Fang, Runyue, Dong, Qiao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Wiley 01.03.2021
Témata:
ISSN:1751-8644, 1751-8652
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local estimation and communication, without any central coordinator. An online distributed conditional gradient algorithm based on the conditional gradient is developed, which can effectively tackle the problem of high time complexity of the distributed online optimisation. The proposed algorithm allows the global objective function to be decomposed into the sum of the local objective functions, and nodes collectively minimise the sum of local time‐varying objective functions while the communication pattern among nodes is captured as a connected undirected graph. By adding a regularisation term to the local objective function of each node, the proposed algorithm constructs a new time‐varying objective function. The proposed algorithm also utilises the local linear optimisation oracle to replace the projection operation such that the regret bound of the algorithm can be effectively improved. By introducing the nominal regret and the global regret, the convergence properties of the proposed algorithm are also theoretically analysed. It is shown that, if the objective function of each agent is strongly convex and smooth, these two types of regrets grow sublinearly with the order of O(logT), where T is the time horizon. Numerical experiments also demonstrate the advantages of the proposed algorithm over existing distributed optimisation algorithms.
AbstractList This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local estimation and communication, without any central coordinator. An online distributed conditional gradient algorithm based on the conditional gradient is developed, which can effectively tackle the problem of high time complexity of the distributed online optimisation. The proposed algorithm allows the global objective function to be decomposed into the sum of the local objective functions, and nodes collectively minimise the sum of local time‐varying objective functions while the communication pattern among nodes is captured as a connected undirected graph. By adding a regularisation term to the local objective function of each node, the proposed algorithm constructs a new time‐varying objective function. The proposed algorithm also utilises the local linear optimisation oracle to replace the projection operation such that the regret bound of the algorithm can be effectively improved. By introducing the nominal regret and the global regret, the convergence properties of the proposed algorithm are also theoretically analysed. It is shown that, if the objective function of each agent is strongly convex and smooth, these two types of regrets grow sublinearly with the order of , where is the time horizon. Numerical experiments also demonstrate the advantages of the proposed algorithm over existing distributed optimisation algorithms.
This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local estimation and communication, without any central coordinator. An online distributed conditional gradient algorithm based on the conditional gradient is developed, which can effectively tackle the problem of high time complexity of the distributed online optimisation. The proposed algorithm allows the global objective function to be decomposed into the sum of the local objective functions, and nodes collectively minimise the sum of local time‐varying objective functions while the communication pattern among nodes is captured as a connected undirected graph. By adding a regularisation term to the local objective function of each node, the proposed algorithm constructs a new time‐varying objective function. The proposed algorithm also utilises the local linear optimisation oracle to replace the projection operation such that the regret bound of the algorithm can be effectively improved. By introducing the nominal regret and the global regret, the convergence properties of the proposed algorithm are also theoretically analysed. It is shown that, if the objective function of each agent is strongly convex and smooth, these two types of regrets grow sublinearly with the order of O(logT), where T is the time horizon. Numerical experiments also demonstrate the advantages of the proposed algorithm over existing distributed optimisation algorithms.
Abstract This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local estimation and communication, without any central coordinator. An online distributed conditional gradient algorithm based on the conditional gradient is developed, which can effectively tackle the problem of high time complexity of the distributed online optimisation. The proposed algorithm allows the global objective function to be decomposed into the sum of the local objective functions, and nodes collectively minimise the sum of local time‐varying objective functions while the communication pattern among nodes is captured as a connected undirected graph. By adding a regularisation term to the local objective function of each node, the proposed algorithm constructs a new time‐varying objective function. The proposed algorithm also utilises the local linear optimisation oracle to replace the projection operation such that the regret bound of the algorithm can be effectively improved. By introducing the nominal regret and the global regret, the convergence properties of the proposed algorithm are also theoretically analysed. It is shown that, if the objective function of each agent is strongly convex and smooth, these two types of regrets grow sublinearly with the order of O(logT), where T is the time horizon. Numerical experiments also demonstrate the advantages of the proposed algorithm over existing distributed optimisation algorithms.
Author Dong, Qiao
Fang, Runyue
Li, Dequan
Shen, Xiuyu
Author_xml – sequence: 1
  givenname: Xiuyu
  surname: Shen
  fullname: Shen, Xiuyu
  organization: Anhui University of Science and Technology
– sequence: 2
  givenname: Dequan
  surname: Li
  fullname: Li, Dequan
  email: leedqcpp@126.com
  organization: Anhui University of Science and Technology
– sequence: 3
  givenname: Runyue
  surname: Fang
  fullname: Fang, Runyue
  organization: Anhui University of Science and Technology
– sequence: 4
  givenname: Qiao
  surname: Dong
  fullname: Dong, Qiao
  organization: Anhui University of Science and Technology
BookMark eNp9kEtLQzEQhYNUsFY3_oKshdY8b-5dlqK2IOiirkOaTGrqbVJyI0V_vX2oCxFXMwznO8w556gXUwSErigZUSKaG1te2IgyUrET1KdK0mFdSdb72YU4Q-ddtyJEykrIPnoaY5uiCyWkaFq8zMYFiAWbdplyKC9r7FPGLnQlh8VbAYdTbEMEnDYlrMOH2YM4RByhbFN-7S7QqTdtB5dfc4Ce727nk-nw4fF-Nhk_DC1Xkg0Z1KKmykFTG8Utp7ZWXpHGOE-UrawCzqSXDihpGlYzwhw3hksrATgIzgdodvR1yaz0Joe1ye86maAPh5SX2uQSbAuaSmmIJ4KrGoRii4WqpKCs8VVtTcX8zoscvWxOXZfBaxvKIVnJJrSaEr1vV-_b1Yd2d8j1L-T7hT_F9Cjehhbe_1HqyXzKjswneo-Mlw
CitedBy_id crossref_primary_10_1002_rnc_6568
crossref_primary_10_1049_cth2_12421
Cites_doi 10.1109/TSP.2018.2830299
10.1109/TAC.2008.2009515
10.1137/080716542
10.1137/S0036144503423264
10.1109/TSP.2017.2771731
10.1109/TAC.2011.2161027
10.1049/iet-cta.2018.5585
10.1109/TNSE.2014.2363554
10.1137/18M119046X
10.1109/CDC.2013.6760092
10.1109/TAC.2014.2298712
10.1109/TKDE.2012.191
10.1007/s10957-010-9737-7
10.1049/iet-cta.2019.0020
10.1002/nav.3800030109
10.1109/TAC.2019.2937496
10.1109/TCNS.2015.2505149
10.1137/140985366
10.1038/30918
10.1137/1.9781611970791
10.1007/s10994-007-5016-8
10.1002/rnc.5199
10.1049/iet-cta.2017.0064
10.1109/TAC.2019.2930234
10.1109/TAC.2010.2041686
10.1016/j.automatica.2018.11.056
ContentType Journal Article
Copyright 2020 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology
Copyright_xml – notice: 2020 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology
DBID 24P
AAYXX
CITATION
DOA
DOI 10.1049/cth2.12062
DatabaseName Wiley Online Library Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef


Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1751-8652
EndPage 579
ExternalDocumentID oai_doaj_org_article_155a0f04378e472bb7654129f68ca62f
10_1049_cth2_12062
CTH212062
Genre article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 61472003
GroupedDBID .DC
0R~
0ZK
1OC
24P
29I
3V.
4.4
4IJ
5GY
6IK
8FE
8FG
8VB
96U
AAHHS
AAHJG
AAJGR
ABJCF
ABQXS
ABUWG
ACCFJ
ACCMX
ACESK
ACGFS
ACIWK
ACXQS
ADEYR
AEEZP
AEGXH
AENEX
AEQDE
AFAZI
AFKRA
AIWBW
AJBDE
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ARAPS
AVUZU
AZQEC
BENPR
BGLVJ
BPHCQ
CCPQU
CS3
DU5
DWQXO
EBS
EJD
ESX
F8P
GNUQQ
GOZPB
GROUPED_DOAJ
GRPMH
HCIFZ
HZ~
IAO
IFIPE
IPLJI
ITC
JAVBF
K1G
K6V
K7-
L6V
LAI
M0N
M43
M7S
MCNEO
MS~
NADUK
NXXTH
O9-
OCL
OK1
P62
PQQKQ
PROAC
PTHSS
QWB
RIE
RNS
ROL
RUI
U5U
UNMZH
ZL0
~ZZ
AAMMB
AAYXX
AEFGJ
AFFHD
AGXDD
AIDQK
AIDYY
CITATION
IDLOA
IGS
PHGZM
PHGZT
PQGLB
WIN
ID FETCH-LOGICAL-c3752-2e84817de98a73c31c87f709adf07c6c7e325f5de109928202d3aa35c5ee3e433
IEDL.DBID 24P
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000602729400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1751-8644
IngestDate Fri Oct 03 12:42:33 EDT 2025
Wed Oct 29 21:29:30 EDT 2025
Tue Nov 18 21:06:23 EST 2025
Wed Jan 22 16:58:37 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License Attribution
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3752-2e84817de98a73c31c87f709adf07c6c7e325f5de109928202d3aa35c5ee3e433
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fcth2.12062
PageCount 10
ParticipantIDs doaj_primary_oai_doaj_org_article_155a0f04378e472bb7654129f68ca62f
crossref_citationtrail_10_1049_cth2_12062
crossref_primary_10_1049_cth2_12062
wiley_primary_10_1049_cth2_12062_CTH212062
PublicationCentury 2000
PublicationDate March 2021
2021-03-00
2021-03-01
PublicationDateYYYYMMDD 2021-03-01
PublicationDate_xml – month: 03
  year: 2021
  text: March 2021
PublicationDecade 2020
PublicationTitle IET control theory & applications
PublicationYear 2021
Publisher Wiley
Publisher_xml – name: Wiley
References 2010; 55
2013; 25
2017; 4
2012
2019; 13
2017; 66
2010; 147
2019; 57
2004; 46
1996
2020; 14
2018; 66
2012; 57
1998; 393
2019; 101
2014; 1
2009; 54
1990
2020; 30
2017; 11
2014; 59
2005; 6
2017
1994; 13
2017; 18
2020; 65
2013
2009; 2
2016; 26
2016; 48
1956; 3
2007; 69
e_1_2_7_6_1
e_1_2_7_5_1
e_1_2_7_4_1
Horn R.A. (e_1_2_7_26_1) 1990
e_1_2_7_3_1
e_1_2_7_9_1
e_1_2_7_8_1
e_1_2_7_7_1
e_1_2_7_19_1
e_1_2_7_18_1
e_1_2_7_17_1
e_1_2_7_2_1
e_1_2_7_15_1
e_1_2_7_13_1
e_1_2_7_12_1
e_1_2_7_11_1
e_1_2_7_10_1
e_1_2_7_29_1
Colin I. (e_1_2_7_31_1) 2016; 48
Xu H. (e_1_2_7_14_1) 2005; 6
Hiriart‐Urruty J. B. (e_1_2_7_28_1) 1996
e_1_2_7_30_1
e_1_2_7_25_1
e_1_2_7_24_1
e_1_2_7_32_1
e_1_2_7_23_1
e_1_2_7_33_1
e_1_2_7_34_1
e_1_2_7_21_1
e_1_2_7_20_1
Kasai H. (e_1_2_7_27_1) 2017; 18
Zhang W. (e_1_2_7_16_1) 2017
Hazan E. (e_1_2_7_22_1) 2012
References_xml – volume: 147
  start-page: 516
  year: 2010
  end-page: 545
  article-title: Distributed stochastic subgradient projection algorithms for convex optimization
  publication-title: J. Optim. Theory Appl.
– volume: 6
  start-page: 1595
  year: 2005
  end-page: 1599
  article-title: Decentralized online alternating direction method of multipliers
  publication-title: J. Comput. Appl.
– start-page: 484
  year: 2013
  end-page: 1489
– start-page: 521
  year: 2012
  end-page: 528
– start-page: 4054
  year: 2017
  end-page: 4062
– volume: 4
  start-page: 417
  year: 2017
  end-page: 428
  article-title: Distributed online convex optimization on time‐varying directed graphs
  publication-title: IEEE Trans. Control Netw. Syst.
– volume: 30
  start-page: 7574
  year: 2020
  end-page: 7592
  article-title: Distributed proximal‐gradient algorithms for nonsmooth convex optimization of second‐order multiagent systems
  publication-title: Int. J. Robust Nonlinear Control
– volume: 54
  start-page: 48
  year: 2009
  end-page: 61
  article-title: Distributed subgradient methods for multi‐agent optimization
  publication-title: IEEE Trans. Autom. Control
– volume: 25
  start-page: 2483
  year: 2013
  end-page: 2493
  article-title: Distributed autonomous online learning: regrets and intrinsic privacy‐preserving properties
  publication-title: IEEE Trans. Knowl. Data Eng.
– year: 1996
– volume: 46
  start-page: 667
  year: 2004
  end-page: 689
  article-title: Fastest mixing Markov chain on a graph
  publication-title: SIAM Rev.
– volume: 26
  start-page: 1493
  year: 2016
  end-page: 1528
  article-title: A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization
  publication-title: SIAM Journal on Optimization
– year: 1990
– volume: 66
  start-page: 3240
  year: 2018
  end-page: 3255
  article-title: Decentralized online learning with kernels
  publication-title: IEEE Trans. Signal Process.
– volume: 57
  start-page: 592
  year: 2012
  end-page: 606
  article-title: Dual averaging for distributed optimization: convergence analysis and network scaling
  publication-title: IEEE Trans. Autom. Control
– volume: 393
  start-page: 440
  year: 1998
  article-title: Collective dynamics of ‘small‐world’ networks
  publication-title: Nature
– volume: 65
  start-page: 2494
  year: 2020
  end-page: 2509
  article-title: Asyspa: an exact asynchronous algorithm for convex optimization over digraphs
  publication-title: IEEE Trans. Autom. Control
– volume: 101
  start-page: 175
  year: 2019
  end-page: 181
  article-title: Distributed quasi‐monotone subgradient algorithm for nonsmooth convex optimization over directed graphs
  publication-title: Automatica
– volume: 57
  start-page: 2821
  year: 2019
  end-page: 2842
  article-title: Distributed subgradient‐free stochastic optimization algorithm for nonsmooth convex functions over time‐varying networks
  publication-title: SIAM J. Control Optim.
– volume: 2
  start-page: 183
  year: 2009
  end-page: 202
  article-title: A fast iterative shrinkage‐thresholding algorithm for linear inverse problems
  publication-title: SIAM J. Imaging Sci.
– volume: 14
  start-page: 549
  year: 2020
  end-page: 557
  article-title: Distributed optimisation based on multi‐agent system for resource allocation with communication time‐delay
  publication-title: IET Control Theory Appl.
– volume: 1
  start-page: 23
  year: 2014
  end-page: 37
  article-title: Distributed online convex optimization over jointly connected digraphs
  publication-title: IEEE Trans. Netw. Sci. Eng.
– volume: 18
  start-page: 7942
  year: 2017
  end-page: 7946
  article-title: SGDLibrary: A MATLAB library for stochastic optimization algorithms
  publication-title: J. Mach. Learn. Res.
– volume: 3
  start-page: 95
  year: 1956
  end-page: 110
  article-title: An algorithm for quadratic programming
  publication-title: Nav. Res. Logist. Q.
– volume: 59
  start-page: 1131
  year: 2014
  end-page: 1146
  article-title: Fast distributed gradient methods
  publication-title: IEEE Trans. Autom. Control
– volume: 11
  start-page: 2549
  year: 2017
  end-page: 2558
  article-title: Distributed optimisation of second‐order multi‐agent systems by control algorithm using position‐only interaction with timevarying delay
  publication-title: IET Control Theory Appl.
– volume: 69
  start-page: 169
  year: 2007
  end-page: 192
  article-title: Logarithmic regret algorithms for online convex optimization
  publication-title: Mach. Lear.
– volume: 55
  start-page: 922
  year: 2010
  end-page: 938
  article-title: Constrained consensus and optimization in multi‐agent networks
  publication-title: IEEE Trans. Autom. Control
– volume: 48
  start-page: 1388
  year: 2016
  end-page: 1396
  article-title: Gossip dual averaging for decentralized optimization of pairwise functions. In Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML 16)
  publication-title: JMLR.org
– volume: 13
  year: 1994
  article-title: Interior‐point polynomial algorithms in convex programming
  publication-title: Soc. Ind. Appl. Math.
– volume: 13
  start-page: 2811
  year: 2019
  end-page: 2816
  article-title: Distributed quadratic optimisation for linear multi‐agent systems over jointly connected networks
  publication-title: IET Control Theory Appl.
– volume: 66
  start-page: 682
  year: 2017
  end-page: 697
  article-title: Node‐specific diffusion LMS‐based distributed detection over adaptive networks
  publication-title: IEEE Trans. Signal Process.
– volume: 65
  start-page: 2566
  year: 2020
  end-page: 2581
  article-title: Accelerated distributed Nesterov gradient descent
  publication-title: IEEE Trans. Autom. Control
– ident: e_1_2_7_5_1
  doi: 10.1109/TSP.2018.2830299
– ident: e_1_2_7_10_1
  doi: 10.1109/TAC.2008.2009515
– ident: e_1_2_7_18_1
  doi: 10.1137/080716542
– volume: 48
  start-page: 1388
  year: 2016
  ident: e_1_2_7_31_1
  article-title: Gossip dual averaging for decentralized optimization of pairwise functions. In Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML 16)
  publication-title: JMLR.org
– ident: e_1_2_7_29_1
  doi: 10.1137/S0036144503423264
– ident: e_1_2_7_9_1
  doi: 10.1109/TSP.2017.2771731
– ident: e_1_2_7_25_1
  doi: 10.1109/TAC.2011.2161027
– ident: e_1_2_7_3_1
  doi: 10.1049/iet-cta.2018.5585
– ident: e_1_2_7_13_1
  doi: 10.1109/TNSE.2014.2363554
– ident: e_1_2_7_32_1
  doi: 10.1137/18M119046X
– start-page: 521
  volume-title: International Conference on Machine Learning, Edinburg
  year: 2012
  ident: e_1_2_7_22_1
– ident: e_1_2_7_15_1
  doi: 10.1109/CDC.2013.6760092
– ident: e_1_2_7_11_1
  doi: 10.1109/TAC.2014.2298712
– volume-title: Convex Analysis and Minimization Algorithms I'
  year: 1996
  ident: e_1_2_7_28_1
– ident: e_1_2_7_2_1
  doi: 10.1109/TKDE.2012.191
– volume-title: Matrix Analysis
  year: 1990
  ident: e_1_2_7_26_1
– ident: e_1_2_7_19_1
  doi: 10.1007/s10957-010-9737-7
– ident: e_1_2_7_4_1
  doi: 10.1049/iet-cta.2019.0020
– start-page: 4054
  volume-title: Proceedings of the 34th International Conference on Machine Learning, Sidney, August
  year: 2017
  ident: e_1_2_7_16_1
– ident: e_1_2_7_17_1
  doi: 10.1002/nav.3800030109
– ident: e_1_2_7_6_1
  doi: 10.1109/TAC.2019.2937496
– volume: 18
  start-page: 7942
  year: 2017
  ident: e_1_2_7_27_1
  article-title: SGDLibrary: A MATLAB library for stochastic optimization algorithms
  publication-title: J. Mach. Learn. Res.
– ident: e_1_2_7_12_1
  doi: 10.1109/TCNS.2015.2505149
– ident: e_1_2_7_23_1
  doi: 10.1137/140985366
– ident: e_1_2_7_30_1
  doi: 10.1038/30918
– ident: e_1_2_7_20_1
  doi: 10.1137/1.9781611970791
– volume: 6
  start-page: 1595
  year: 2005
  ident: e_1_2_7_14_1
  article-title: Decentralized online alternating direction method of multipliers
  publication-title: J. Comput. Appl.
– ident: e_1_2_7_21_1
  doi: 10.1007/s10994-007-5016-8
– ident: e_1_2_7_34_1
  doi: 10.1002/rnc.5199
– ident: e_1_2_7_8_1
  doi: 10.1049/iet-cta.2017.0064
– ident: e_1_2_7_7_1
  doi: 10.1109/TAC.2019.2930234
– ident: e_1_2_7_24_1
  doi: 10.1109/TAC.2010.2041686
– ident: e_1_2_7_33_1
  doi: 10.1016/j.automatica.2018.11.056
SSID ssj0055645
Score 2.312362
Snippet This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of the local...
Abstract This paper addresses a network of computing nodes aiming to solve an online convex optimisation problem in a distributed manner, that is, by means of...
SourceID doaj
crossref
wiley
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 570
SubjectTerms Combinatorial mathematics
Computational complexity
Interpolation and function approximation (numerical analysis)
Optimisation techniques
Parallel programming and algorithm theory
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA4iHvQgPrG-COhFIbpNNpvNsYqlJ_FQobclTy20W2lXf7-TZFsURC_elmUgyzdhvpnN5BuELr22FohHEQiQkuRAWERBWkxywYwAfhJapmET4vGxHI3k05dRX6EnLMkDJ-Buge9U5oMCT-lyQbUWYXI1lb4ojSqoD9EXsp5lMZViMA8aKfEqJO-SEih_KUyay1vTvNKbLs0K-o2KomL_9ww1Ukx_B223uSHupW_aRWuu3kNbXxQD99FTD0MBa8fpDx5-mceOrQarycsMyvzXKYYkFNughhsGWTmLkxQGnkFomLZ3LvG4xnVq_14coOf-w_B-QNqhCMQwwSmhLgjgC-tkqQBP1jWl8ICqsj4TpjDCMco9ty4ceUE9lVHLlGLccOeYyxk7ROv1rHZHCFOdmYIblWlrcsm8NJp1FRc6tx7KON1BV0t8KtMqhofBFZMqnlznsgpYVhHLDrpY2b4lnYwfre4CzCuLoG0dX4DHq9bj1V8e76Dr6KRf1qnuhwMan47_Y8UTtElDK0tsPTtF68383Z2hDfPRjBfz87jzPgFe3tm9
  priority: 102
  providerName: Directory of Open Access Journals
Title A conditional gradient algorithm for distributed online optimization in networks
URI https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fcth2.12062
https://doaj.org/article/155a0f04378e472bb7654129f68ca62f
Volume 15
WOSCitedRecordID wos000602729400001&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: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1751-8652
  dateEnd: 20241231
  omitProxy: false
  ssIdentifier: ssj0055645
  issn: 1751-8644
  databaseCode: DOA
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-8652
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0055645
  issn: 1751-8644
  databaseCode: 24P
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-8652
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0055645
  issn: 1751-8644
  databaseCode: WIN
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8QwFA6iHvTgLo4bAb0oVNsskwa8qCh6Geag6K1kHQfGjtTq7_cl7YwKIoiXUsoLDXnJW5KX70Po0GtrwfGoBAykTBg4rERBWJwwQY0A_yS0bMgmRK-XPz7K_gw6m9yFafAhphtuYWVEex0WuNINCwkEtaBEUz-Rk4ykwQDPZRnNA3EDYf2JHeYBJyVeh-RZkoPbn4CTMnn62fabO4qo_d-j1Ohmrpf_18EVtNSGl_i8mQ-raMaVa2jxC-jgOuqfY8iB7bDZBMSDKhZ91ViNBuNqWD89Y4hjsQ2AuoELy1ncdAaPwbo8t9c28bDEZVNB_rqB7q-v7i5vkpZXITFUcJIQFzD0hXUyV6ASmplceFCMsj4VpmuEo4R7bl04NYOULCWWKkW54c5RxyjdRLPluHRbCBOdmi43KtXWMEm9NJpmigvNrIdMUHfQ0WR4C9OCjgfui1ERD7-ZLMIoFXGUOuhgKvvSQG38KHURtDSVCPDY8cO4GhTtaisgSFKpD7BNuWOCaC0C3TmRvpsb1SW-g46j5n75T3F5d0Pi2_ZfhHfQAglVL7FKbRfN1tWb20Pz5r0evlb7cYLux7wfng-3vQ_qIujN
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSyNBEG6WuOB6cNcXRvfRoBcXRif9SE8f3bAhYTXkEDG3oZ8xoBMZR3-_XT2TqLAsyN6GoYZpurqeXfUVQsdeWxsMj0qCgpQJCwYrUcEtTpigRgT7JLSsh02I0SibTuW4qc2BXpgaH2KVcAPJiPoaBBwS0nXAyQAk01Q35LRDUtDAayx4GjC54Xo4WipiDkApsR-Sd5Is2P0lOimTZy_fvrFHEbb_rZsa7Uz_83-u8AvabBxMfF6fiC30wRXbaOMV7OAOGp_jEAXbeZ0GxLMyln1VWN3OFuW8urnDwZPFFiB1YRqWs7heDV4E_XLXNG7ieYGLuob8YRdd9X9PeoOkmayQGCo4SYgDFH1hncxUYArtmEz4wBplfSpM1whHCffcOrg3C0FZSixVinLDnaOOUbqHWsWicPsIE52aLjcq1dYwSb00mnYUF5pZH2JB3UYny_3NTQM7DtMvbvN4_c1kDruUx11qo6MV7X0NtvFXql_AphUFAGTHF4tyljfylgc3SaUegJsyxwTRWsDAcyJ9NzOqS3wb_Yys-8d_8t5kQOLTwXuIf6D1weTyIr8Yjv4cok8EamBizdpX1KrKR_cNfTRP1fyh_B5P6zNsaOsh
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSxtBFB-KFrEHba1iqrYDelFY3Z2PzM5R0wZLJeSgkNsyn0kg2ci69u_vvNlNVJCCeFuWt-ww73vmvd9D6MRra4PjUUkwkDJhwWElKoTFCRPUiOCfhJbNsAkxGOSjkRy2tTnQC9PgQ6wO3EAzor0GBXf31jcJJwOQTFNPyHlGUrDA64yLDISasOHSEHMASon9kDxL8uD3l-ikTF48ffvCH0XY_pdhavQz_e13rvAz2moDTHzZSMQX9MGVO-jTM9jBr2h4iUMWbKfNMSAeV7Hsq8ZqNl5U03oyxyGSxRYgdWEalrO4WQ1eBPsybxs38bTEZVND_rCL7vq_bnvXSTtZITFUcJIQByj6wjqZq8AUmplc-MAaZX0qTNcIRwn33Dq4NwtJWUosVYpyw52jjlG6h9bKRen2ESY6NV1uVKqtYZJ6aTTNFBeaWR9yQd1Bp8v9LUwLOw7TL2ZFvP5msoBdKuIuddDxiva-Adt4leoK2LSiAIDs-GJRjYtW34oQJqnUA3BT7pggWgsYeE6k7-ZGdYnvoLPIuv_8p-jdXpP49O0txD_QxvBnv7j5PfhzgDYJlMDEkrVDtFZXj-4IfTR_6-lD9T0K6z-ehuo4
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=A+conditional+gradient+algorithm+for+distributed+online+optimization+in+networks&rft.jtitle=IET+control+theory+%26+applications&rft.au=Shen%2C+Xiuyu&rft.au=Li%2C+Dequan&rft.au=Fang%2C+Runyue&rft.au=Dong%2C+Qiao&rft.date=2021-03-01&rft.issn=1751-8644&rft.eissn=1751-8652&rft.volume=15&rft.issue=4&rft.spage=570&rft.epage=579&rft_id=info:doi/10.1049%2Fcth2.12062&rft.externalDBID=10.1049%252Fcth2.12062&rft.externalDocID=CTH212062
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-8644&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-8644&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-8644&client=summon