Compressed Gradient Tracking Algorithm for Distributed Aggregative Optimization

This article is devoted to addressing the distributed aggregative optimization (DAO) problem via compressed gradient tracking algorithms, where the cost function of each agent relies on the aggregation of other agents' decisions as well as its own decision. To this end, a new kind of the distri...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on automatic control Ročník 69; číslo 10; s. 6576 - 6591
Hlavní autoři: Chen, Liyuan, Wen, Guanghui, Liu, Hongzhe, Yu, Wenwu, Cao, Jinde
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:0018-9286, 1558-2523
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This article is devoted to addressing the distributed aggregative optimization (DAO) problem via compressed gradient tracking algorithms, where the cost function of each agent relies on the aggregation of other agents' decisions as well as its own decision. To this end, a new kind of the distributed aggregative gradient tracking algorithm with compression communication is developed based on the gradient tracking algorithm and the technique of communication compression. Under the scenario with a time-invariant and balanced graph, it is theoretically shown that the present algorithm owns a linear convergence rate (in the mean-square error sense) with the strongly convex and smooth cost functions. Furthermore, the result is extended to a more general case with the time-varying graphs considered. Specifically, it is proven that the developed algorithm could converge linearly to the optimal solution of the DAO problem (in the mean-square error sense) if the time-varying balanced graph is jointly strongly connected and some suitable conditions are satisfied. With the optimal placement problem considered, some numerical simulation results are performed to validate the theoretical results.
AbstractList This article is devoted to addressing the distributed aggregative optimization (DAO) problem via compressed gradient tracking algorithms, where the cost function of each agent relies on the aggregation of other agents' decisions as well as its own decision. To this end, a new kind of the distributed aggregative gradient tracking algorithm with compression communication is developed based on the gradient tracking algorithm and the technique of communication compression. Under the scenario with a time-invariant and balanced graph, it is theoretically shown that the present algorithm owns a linear convergence rate (in the mean-square error sense) with the strongly convex and smooth cost functions. Furthermore, the result is extended to a more general case with the time-varying graphs considered. Specifically, it is proven that the developed algorithm could converge linearly to the optimal solution of the DAO problem (in the mean-square error sense) if the time-varying balanced graph is jointly strongly connected and some suitable conditions are satisfied. With the optimal placement problem considered, some numerical simulation results are performed to validate the theoretical results.
Author Cao, Jinde
Wen, Guanghui
Yu, Wenwu
Chen, Liyuan
Liu, Hongzhe
Author_xml – sequence: 1
  givenname: Liyuan
  orcidid: 0009-0007-4171-0665
  surname: Chen
  fullname: Chen, Liyuan
  email: clymath@seu.edu.cn
  organization: Department of Systems Science, School of Mathematics, Southeast University, Nanjing, China
– sequence: 2
  givenname: Guanghui
  orcidid: 0000-0003-0070-8597
  surname: Wen
  fullname: Wen, Guanghui
  email: ghwen@seu.edu.cn
  organization: Department of Systems Science, School of Mathematics, Southeast University, Nanjing, China
– sequence: 3
  givenname: Hongzhe
  orcidid: 0000-0002-6887-368X
  surname: Liu
  fullname: Liu, Hongzhe
  email: 101300130@seu.edu.cn
  organization: Department of Systems Science, School of Mathematics, Southeast University, Nanjing, China
– sequence: 4
  givenname: Wenwu
  orcidid: 0000-0003-0301-9180
  surname: Yu
  fullname: Yu, Wenwu
  email: wwyu@seu.edu.cn
  organization: Department of Systems Science, School of Mathematics, Southeast University, Nanjing, China
– sequence: 5
  givenname: Jinde
  orcidid: 0000-0003-3133-7119
  surname: Cao
  fullname: Cao, Jinde
  email: jdcao@seu.edu.cn
  organization: School of Mathematics, Southeast University, Nanjing, China
BookMark eNp9kDtPwzAURi1UJNrCzsAQiTnFr8TxGAUoSJW6lNlybCe4NA9sFwl-PS7tgBiYrj7pO_denRmY9ENvALhGcIEQ5HebslpgiOmCEIYKlp-BKcqyIsUZJhMwhRAVKcdFfgFm3m9jzClFU7Cuhm50xnujk6WT2po-JBsn1Zvt26TctYOz4bVLmsEl99YHZ-t9iN2ybZ1pZbAfJlmPwXb2K4ahvwTnjdx5c3Wac_Dy-LCpntLVevlclatUYY5DinKoOa0NMcxwIiFTUhWcE8JrRLCWWVGzGiIGc10QrThEjZE5IlpLojJGyRzcHveObnjfGx_Edti7Pp4UJPqgjGWUx1Z-bCk3eO9MI5QNP38GJ-1OICgO8kSUJw7yxEleBOEfcHS2k-7zP-TmiFhjzK86zQgnlHwDggB8Xg
CODEN IETAA9
CitedBy_id crossref_primary_10_1016_j_neunet_2024_107085
crossref_primary_10_1016_j_sysconle_2025_106217
crossref_primary_10_1109_TSIPN_2025_3603740
crossref_primary_10_1016_j_neucom_2024_129022
Cites_doi 10.1109/tac.2024.3368967
10.1109/tnse.2023.3253143
10.1109/CDC49753.2023.10384194
10.1109/MSP.2020.2975210
10.1109/cdc51059.2022.9993052
10.1109/tac.2021.3095456
10.1109/TAC.2016.2626578
10.1109/TCNS.2014.2357513
10.1109/TCNS.2017.2698261
10.1016/j.ifacol.2022.07.227
10.1142/p821
10.1109/TSP.2019.2926022
10.1137/14096668X
10.1109/TAC.2022.3154356
10.1109/tac.2023.3241771
10.14736/kyb-2022-1-0123
10.1109/TAC.2020.3014095
10.1109/tac.2022.3145576
10.1002/rnc.6640
10.1109/tac.2022.3219289
10.1007/978-1-4419-8853-9
10.1137/16M1084316
10.1109/TAC.2020.2989281
10.1017/CBO9781139020411
10.1109/CDC45484.2021.9683433
10.1109/tac.2022.3180695
10.1109/TAC.2008.2009515
10.1109/TCNS.2021.3107480
10.1109/tac.2022.3225515
10.1109/TSP.2020.3031073
10.1109/TCNS.2018.2834310
10.1109/TSP.2022.3160238
10.1109/TAC.2022.3196627
10.1109/TAC.2020.2969721
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
DOI 10.1109/TAC.2024.3371876
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2523
EndPage 6591
ExternalDocumentID 10_1109_TAC_2024_3371876
10453934
Genre orig-research
GrantInformation_xml – fundername: National Key Research and Development Program of China
  grantid: 2022YFA1004702
– fundername: Jiangsu Provincial Scientific Research Center of Applied Mathematics
  grantid: BK20233002
– fundername: National Natural Science Foundation of China
  grantid: 62325304; U22B2046; 62073079; 61833005; 62088101; 62233004; 62203110; 62073076
  funderid: 10.13039/501100001809
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
VJK
~02
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c292t-160d94be3e7e93a07cac899339b132da58b7b01706d83dc901fea613dda3c5743
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001322635200012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9286
IngestDate Mon Jun 30 10:07:11 EDT 2025
Sat Nov 29 05:41:11 EST 2025
Tue Nov 18 22:24:33 EST 2025
Wed Aug 27 02:02:24 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c292t-160d94be3e7e93a07cac899339b132da58b7b01706d83dc901fea613dda3c5743
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-6887-368X
0000-0003-0301-9180
0009-0007-4171-0665
0000-0003-0070-8597
0000-0003-3133-7119
PQID 3110477549
PQPubID 85475
PageCount 16
ParticipantIDs crossref_citationtrail_10_1109_TAC_2024_3371876
crossref_primary_10_1109_TAC_2024_3371876
ieee_primary_10453934
proquest_journals_3110477549
PublicationCentury 2000
PublicationDate 2024-10-01
PublicationDateYYYYMMDD 2024-10-01
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-10-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on automatic control
PublicationTitleAbbrev TAC
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref35
ref12
ref34
ref15
ref37
ref14
ref36
Koloskova (ref10) 2019
Alistarh (ref11) 2017
ref33
ref2
ref1
Guido (ref30) 2022
ref17
ref39
ref16
ref38
ref19
Liu (ref32) 2023
ref18
ref24
ref23
Liu (ref13) 2020
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
Du (ref31) 2023
ref6
ref5
ref40
References_xml – ident: ref24
  doi: 10.1109/tac.2024.3368967
– ident: ref33
  doi: 10.1109/tnse.2023.3253143
– ident: ref25
  doi: 10.1109/CDC49753.2023.10384194
– start-page: 1576
  volume-title: Proc. IEEE 61st Conf. Decis. Control
  year: 2022
  ident: ref30
  article-title: A learning-based distributed algorithm for personalized aggregative optimization
– ident: ref3
  doi: 10.1109/MSP.2020.2975210
– ident: ref34
  doi: 10.1109/cdc51059.2022.9993052
– ident: ref22
  doi: 10.1109/tac.2021.3095456
– ident: ref2
  doi: 10.1109/TAC.2016.2626578
– ident: ref16
  doi: 10.1109/TCNS.2014.2357513
– ident: ref7
  doi: 10.1109/TCNS.2017.2698261
– ident: ref23
  doi: 10.1016/j.ifacol.2022.07.227
– ident: ref36
  doi: 10.1142/p821
– ident: ref4
  doi: 10.1109/TSP.2019.2926022
– ident: ref5
  doi: 10.1137/14096668X
– ident: ref26
  doi: 10.1109/TAC.2022.3154356
– ident: ref8
  doi: 10.1109/tac.2023.3241771
– start-page: 3478
  volume-title: Proc. 36th Int. Conf. Mach. Learn.
  year: 2019
  ident: ref10
  article-title: Decentralized stochastic optimization and gossip algorithms with compressed communication
– volume-title: Proc. Int. Conf. Learn. Representations
  year: 2020
  ident: ref13
  article-title: Linear convergent decentralized optimization with compression
– ident: ref35
  doi: 10.14736/kyb-2022-1-0123
– ident: ref17
  doi: 10.1109/TAC.2020.3014095
– ident: ref12
  doi: 10.1109/tac.2022.3145576
– year: 2023
  ident: ref31
  article-title: Linear convergence of distributed aggregative optimization with coupled inequality constraints
– ident: ref29
  doi: 10.1002/rnc.6640
– year: 2023
  ident: ref32
  article-title: Accelerated distributed aggregative optimization
– ident: ref20
  doi: 10.1109/tac.2022.3219289
– ident: ref37
  doi: 10.1007/978-1-4419-8853-9
– ident: ref6
  doi: 10.1137/16M1084316
– ident: ref19
  doi: 10.1109/TAC.2020.2989281
– ident: ref38
  doi: 10.1017/CBO9781139020411
– ident: ref21
  doi: 10.1109/CDC45484.2021.9683433
– ident: ref14
  doi: 10.1109/tac.2022.3180695
– ident: ref40
  doi: 10.1109/TAC.2008.2009515
– ident: ref28
  doi: 10.1109/TCNS.2021.3107480
– ident: ref9
  doi: 10.1109/tac.2022.3225515
– ident: ref18
  doi: 10.1109/TSP.2020.3031073
– ident: ref1
  doi: 10.1109/TCNS.2018.2834310
– ident: ref15
  doi: 10.1109/TSP.2022.3160238
– start-page: 1709
  volume-title: Proc. Int. Conf. Adv. Neural Inf. Process. Syst.
  year: 2017
  ident: ref11
  article-title: QSGD: Communication-efficient SGD via gradient quantization and encoding
– ident: ref27
  doi: 10.1109/TAC.2022.3196627
– ident: ref39
  doi: 10.1109/TAC.2020.2969721
SSID ssj0016441
Score 2.4831927
Snippet This article is devoted to addressing the distributed aggregative optimization (DAO) problem via compressed gradient tracking algorithms, where the cost...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 6576
SubjectTerms Algorithms
Communication compression
Compressors
Convergence
Cost function
distributed aggregative optimization (DAO)
Gradient methods
gradient tracking algorithm
Linear matrix inequalities
Machine learning algorithms
Optimization
Prediction algorithms
Time-varying channels
time-varying graph
Tracking
Title Compressed Gradient Tracking Algorithm for Distributed Aggregative Optimization
URI https://ieeexplore.ieee.org/document/10453934
https://www.proquest.com/docview/3110477549
Volume 69
WOSCitedRecordID wos001322635200012&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: PRVIEE
  databaseName: IEEE/IET Electronic Library
  customDbUrl:
  eissn: 1558-2523
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0016441
  issn: 0018-9286
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxQADzyIKBWVgYUib2Ikdj1GhMKCWoUjdIr9SKtEWpSm_n7OTVpUQSGwZ7Ci6yz0-n-87hO6wTGLKsfCZwNSPiIx9LjhgHhYoTLXIpXRTS17YcJhMJvy1blZ3vTDGGHf5zHTto6vl66Va26MysPAoJpxEDdRgjFbNWtuSgQ3sldsFC8bJtiYZ8N447QMSxFGXEHDFll5kJwa5oSo_PLELL4Pjf37YCTqq80gvrRR_ivbM4gwd7rALnqORtXXHDa69p8Jd7So9iE3Kno576cd0WczK97kHaav3YPlz7egrWJtOAYNPHSG4NwKPMq9bNVvobfA47j_79fwEX2GOSz-kgeaRNMQww4kImBIK4BUhXAIG1SJOJJOOP0cnRCvIDHIjILxrLYiKIbW4QM3FcmEukZfQKKdUshznONKKJbGAWM9CLRUTYWjaqLeRaKZqcnE74-IjcyAj4BnoILM6yGodtNH9dsdnRazxx9qWlfnOukrcbdTZaC2rTW-VkdCyTzDAvVe_bLtGB_bt1ZW8DmqWxdrcoH31Vc5Wxa37q74BEoDJkA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwEB2xScCBtYiy5sCFQ9rETuL4WBUKiFI4FIlb5C2lUhdUAt_P2AlVJQQStxxsJZrJLM_jeQNwQWQaJ5wInwmS-BGVsc8FR8zDAkUSLXIp3dSSLuv10pcX_lQ1q7teGGOMu3xmGvbR1fL1VH3YozK08CimnEbLsGpHZ1XtWvOigQ3tpeNFGybpvCoZ8Ga_1UYsSKIGpeiMLcHIQhRyY1V--GIXYDrb__y0HdiqMkmvVap-F5bMZA82F_gF9-HRWrtjB9fezcxd7io8jE7Kno97rdFgOhsWr2MPE1fvyjLo2uFXuLY1QBQ-cJTg3iP6lHHVrFmD5851v33rVxMUfEU4KfwwCTSPpKGGGU5FwJRQCLAo5RJRqBZxKpl0DDo6pVphbpAbgQFea0FVjMnFAaxMphNzCF6aRHmSSJaTnERasTQWGO1ZqKViIgxNHZrfEs1URS9up1yMMgczAp6hDjKrg6zSQR0u5zveSmqNP9bWrMwX1pXirsPJt9ayyvjeMxpa_gmGyPfol23nsH7bf-hm3bve_TFs2DeVF_ROYKWYfZhTWFOfxfB9dub-sC--RczZ
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=Compressed+Gradient+Tracking+Algorithm+for+Distributed+Aggregative+Optimization&rft.jtitle=IEEE+transactions+on+automatic+control&rft.au=Chen%2C+Liyuan&rft.au=Wen%2C+Guanghui&rft.au=Liu%2C+Hongzhe&rft.au=Yu%2C+Wenwu&rft.date=2024-10-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9286&rft.eissn=1558-2523&rft.volume=69&rft.issue=10&rft.spage=6576&rft_id=info:doi/10.1109%2FTAC.2024.3371876&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9286&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9286&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9286&client=summon