Decentralized Approximate Newton Methods for Convex Optimization on Networked Systems

In this article, a class of decentralized approximate Newton (DEAN) methods for addressing convex optimization on a networked system is developed, where nodes in the networked system seek a consensus that minimizes the sum of their individual objective functions through local interactions only. The...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on control of network systems Vol. 8; no. 3; pp. 1489 - 1500
Main Authors Wei, Hejie, Qu, Zhihai, Wu, Xuyang, Wang, Hao, Lu, Jie
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.09.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN2325-5870
2372-2533
DOI10.1109/TCNS.2021.3070663

Cover

Abstract In this article, a class of decentralized approximate Newton (DEAN) methods for addressing convex optimization on a networked system is developed, where nodes in the networked system seek a consensus that minimizes the sum of their individual objective functions through local interactions only. The proposed DEAN algorithms allow each node to repeatedly perform a local approximate Newton update, which leverages tracking the global Newton direction and dissipating the discrepancies among the nodes. Under less restrictive problem assumptions in comparison with most existing second-order methods, the DEAN algorithms enable the nodes to reach a consensus that can be arbitrarily close to the optimum. Moreover, for a particular DEAN algorithm, the nodes linearly converge to a common suboptimal solution with an explicit error bound. Finally, simulations demonstrate the competitive performance of DEAN in convergence speed, accuracy, and efficiency.
AbstractList In this article, a class of decentralized approximate Newton (DEAN) methods for addressing convex optimization on a networked system is developed, where nodes in the networked system seek a consensus that minimizes the sum of their individual objective functions through local interactions only. The proposed DEAN algorithms allow each node to repeatedly perform a local approximate Newton update, which leverages tracking the global Newton direction and dissipating the discrepancies among the nodes. Under less restrictive problem assumptions in comparison with most existing second-order methods, the DEAN algorithms enable the nodes to reach a consensus that can be arbitrarily close to the optimum. Moreover, for a particular DEAN algorithm, the nodes linearly converge to a common suboptimal solution with an explicit error bound. Finally, simulations demonstrate the competitive performance of DEAN in convergence speed, accuracy, and efficiency.
Author Qu, Zhihai
Wu, Xuyang
Lu, Jie
Wei, Hejie
Wang, Hao
Author_xml – sequence: 1
  givenname: Hejie
  surname: Wei
  fullname: Wei, Hejie
  email: 20190057@lixin.edu.cn
  organization: School of Statistics and Mathematics, Shanghai Lixin University of Accounting and Finance, Shanghai, China
– sequence: 2
  givenname: Zhihai
  orcidid: 0000-0003-4996-4583
  surname: Qu
  fullname: Qu, Zhihai
  email: quzhh1@shanghaitech.edu.cn
  organization: College of Electronics and Information Engineering, Tongji University, Shanghai, China
– sequence: 3
  givenname: Xuyang
  orcidid: 0000-0001-7409-9611
  surname: Wu
  fullname: Wu, Xuyang
  email: xuyangw@kth.se
  organization: Division of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden
– sequence: 4
  givenname: Hao
  orcidid: 0000-0001-8821-7260
  surname: Wang
  fullname: Wang, Hao
  email: wanghao1@shanghaitech.edu.cn
  organization: School of Information Science and Technology, ShanghaiTech University, Shanghai, China
– sequence: 5
  givenname: Jie
  orcidid: 0000-0002-4362-6543
  surname: Lu
  fullname: Lu, Jie
  email: lujie@shanghaitech.edu.cn
  organization: School of Information Science and Technology, ShanghaiTech University, Shanghai, China
BackLink https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-303362$$DView record from Swedish Publication Index
BookMark eNp9kEFP2zAYhi0EEh30B6BdIu2czvYXx_GxKmObxMoBytVKnC_D0MaZ7a7Ar5-zdjtwQLJkW34e6_3eD-S4dz0ScsHojDGqPt8tlrczTjmbAZW0LOGITDhInnMBcDyeuchFJekpmYbwSCllXKQ7TMjqEg320ddr-4ptNh8G757tpo6YLXEXXZ_9wPjg2pB1zmcL1__G5-xmiHZjX-to03taS4w755-Sf_sSIm7COTnp6nXA6WE_I6urL3eLb_n1zdfvi_l1bgBYzDtTmIbVtVGyNLTpsDRMSZBF2RRoTCux6SpRGV61DCouq0ZVZdtxJUShqBFwRvL9v2GHw7bRg0_R_Yt2tdWX9n6unf-pn-KDBgpQ8sR_2vNpyl9bDFE_uq3vU0TNhQRRqqIYKbmnjHcheOy0sfHvsKknu9aM6rF2Pdaux9r1ofZksjfmv0TvOR_3jkXE_7wCVUih4A-qwJDB
CODEN ITCNAY
CitedBy_id crossref_primary_10_1109_TSP_2024_3514676
crossref_primary_10_1109_TSIPN_2023_3290397
Cites_doi 10.1109/TSP.2019.2951216
10.1109/TAC.2015.2449811
10.1137/14096668X
10.1109/TAC.2012.2184199
10.1109/ICARCV.2018.8581380
10.1109/TAC.2019.2907711
10.1109/TAC.2011.2167817
10.1109/TCNS.2017.2698261
10.1016/j.automatica.2015.11.014
10.1109/TCNS.2014.2309751
10.1109/TSP.2016.2617829
10.1137/16M1084316
10.1109/TAC.2017.2737582
10.1109/CACSD.2004.1393890
10.1109/TSIPN.2016.2613678
10.1109/TAC.2004.834113
10.1145/984622.984626
10.1109/TAC.2019.2933607
10.1137/130943170
10.1137/15M1038049
10.1016/j.automatica.2018.04.010
10.1109/TAC.2010.2041686
10.1109/TSP.2016.2548989
10.1109/TSP.2017.2666776
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ADTPV
AOWAS
D8V
DOI 10.1109/TCNS.2021.3070663
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
SwePub
SwePub Articles
SWEPUB Kungliga Tekniska Högskolan
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts


Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2372-2533
EndPage 1500
ExternalDocumentID oai_DiVA_org_kth_303362
10_1109_TCNS_2021_3070663
9394759
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Shanghai
  grantid: 16ZR1422500
  funderid: 10.13039/100007219
– fundername: National Natural Science Foundation of China
  grantid: 61603254; 12001367
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
OCL
PQQKQ
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ADTPV
AOWAS
D8V
ID FETCH-LOGICAL-c331t-fc4cb1aac976c0bfe6c1973746b4eccd7ebf858c28d138278b986df2955490c53
IEDL.DBID RIE
ISSN 2325-5870
IngestDate Thu Aug 21 07:31:08 EDT 2025
Mon Jun 30 03:26:51 EDT 2025
Thu Apr 24 23:02:35 EDT 2025
Wed Oct 01 04:44:49 EDT 2025
Wed Aug 27 02:27:19 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
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-c331t-fc4cb1aac976c0bfe6c1973746b4eccd7ebf858c28d138278b986df2955490c53
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-4996-4583
0000-0001-8821-7260
0000-0002-4362-6543
0000-0001-7409-9611
PQID 2573569442
PQPubID 2040410
PageCount 12
ParticipantIDs proquest_journals_2573569442
crossref_citationtrail_10_1109_TCNS_2021_3070663
crossref_primary_10_1109_TCNS_2021_3070663
swepub_primary_oai_DiVA_org_kth_303362
ieee_primary_9394759
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2021-09-01
PublicationDateYYYYMMDD 2021-09-01
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE transactions on control of network systems
PublicationTitleAbbrev TCNS
PublicationYear 2021
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 ref13
bach (ref3) 2014; 15
ref12
ref15
ref14
ref11
ref10
ref2
ref1
ref17
ref16
zhu (ref5) 2012; 57
ref19
ref18
ref24
ref23
ref25
ref20
ref22
ref21
ref8
ref7
ref9
ref4
ref6
References_xml – ident: ref15
  doi: 10.1109/TSP.2019.2951216
– ident: ref21
  doi: 10.1109/TAC.2015.2449811
– ident: ref6
  doi: 10.1137/14096668X
– ident: ref22
  doi: 10.1109/TAC.2012.2184199
– ident: ref23
  doi: 10.1109/ICARCV.2018.8581380
– ident: ref16
  doi: 10.1109/TAC.2019.2907711
– volume: 57
  start-page: 151
  year: 2012
  ident: ref5
  article-title: On distributed convex optimization under inequality and equality constraints
  publication-title: IEEE Trans Autom Control
  doi: 10.1109/TAC.2011.2167817
– ident: ref9
  doi: 10.1109/TCNS.2017.2698261
– ident: ref7
  doi: 10.1016/j.automatica.2015.11.014
– ident: ref2
  doi: 10.1109/TCNS.2014.2309751
– volume: 15
  start-page: 595
  year: 2014
  ident: ref3
  article-title: Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression
  publication-title: J Mach Learn Res
– ident: ref18
  doi: 10.1109/TSP.2016.2617829
– ident: ref10
  doi: 10.1137/16M1084316
– ident: ref11
  doi: 10.1109/TAC.2017.2737582
– ident: ref25
  doi: 10.1109/CACSD.2004.1393890
– ident: ref13
  doi: 10.1109/TSIPN.2016.2613678
– ident: ref24
  doi: 10.1109/TAC.2004.834113
– ident: ref1
  doi: 10.1145/984622.984626
– ident: ref19
  doi: 10.1109/TAC.2019.2933607
– ident: ref8
  doi: 10.1137/130943170
– ident: ref20
  doi: 10.1137/15M1038049
– ident: ref12
  doi: 10.1016/j.automatica.2018.04.010
– ident: ref4
  doi: 10.1109/TAC.2010.2041686
– ident: ref14
  doi: 10.1109/TSP.2016.2548989
– ident: ref17
  doi: 10.1109/TSP.2017.2666776
SSID ssj0001255873
Score 2.2194169
Snippet In this article, a class of decentralized approximate Newton (DEAN) methods for addressing convex optimization on a networked system is developed, where nodes...
SourceID swepub
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1489
SubjectTerms Algorithms
Approximation
Approximation algorithms
Computational geometry
Convergence
Convex analysis
Convex functions
Convexity
Distributed optimization
Linear programming
network optimization
Newton method
Newton methods
Nodes
Optimization
Radio frequency
second-order methods
Title Decentralized Approximate Newton Methods for Convex Optimization on Networked Systems
URI https://ieeexplore.ieee.org/document/9394759
https://www.proquest.com/docview/2573569442
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-303362
Volume 8
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2372-2533
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001255873
  issn: 2325-5870
  databaseCode: RIE
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PSxwxGP1QT-2ham3p-oscSg_FWTP5NclxWRUpuD3UFW9hk0nool2LzoL41_tlJruspYgwhzlMQsj7JnlJXt4H8LUO1HvJYiFcJQvBQihMVKbA2NGmZFGoSavyHanzsfhxLa_X4Gh5FyaE0IrPQj-9tmf59Z2fp62yY8NNsqdbh_VKq-6u1sp-ipS64vngsqTm-HI4-oULQFb2U1wrxV9MPW0ulZe0ctUqtJ1ezjbhYtGwTlVy0583ru-f_vFsfGvLt-BD5plk0AXGNqyF2Ud4v-I-uAPjk5ClmdOnUJNBchd_nCKDDQSHPuSE5KJNL_1AkNiSYZKnP5KfOMT8yXc3CT6jTkaO5bP3-ScYn51eDs-LnGWh8JyXTRG98K6cTDwSE09dDMqXpuKVUE4gvnUVXNRSe6br5FdYaWe0qiMzSEQM9ZJ_ho3Z3Sx8ARJlGSmdKB91WudIx5SMkVHPTO3KWvSALgCwPluQp0wYt7ZdilBjE2Y2YWYzZj34vizyt_PfeO3jndT1yw9zr_dgf4GyzX_og8WhiktlhGA9-NYhvyyXLLdPplcDixjam-Y31s9xot_9f_V78C41ohOe7cNGcz8PB8hUGnfYhugz59rnoQ
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT9swGP3E4LBx2C-GKGObD2iHaSmOfyU-VmWobLQc1k7crNqxtYpREKQS4q_f58StyjRNk3LIIbYsvy_2s_38PoDDylPnJAuZsIXMBPM-00HpDGOn1DkLQk0ble9IDSbi64W82IDPq7sw3vtGfOa78bU5y6-u3SJulR1prqM93RPYkkII2d7WWttRkbIseDq6zKk-GvdH33EJyPJujGyl-KPJp8mm8phYrpuFNhPMyQsYLpvW6kouu4vadt3DH66N_9v2l_A8MU3Sa0PjFWz4-WvYXvMf3IHJsU_izNmDr0gv-ovfz5DDeoKDH7JCMmwSTN8RpLakHwXq9-QcB5mrdHuT4DNqheRYPrmfv4HJyZdxf5ClPAuZ4zyvs-CEs_l06pCaOGqDVy7XBS-EsgIRrgpvQylLx8oqOhYWpdWlqgLTSEU0dZLvwub8eu73gASZB0qnyoUyrnSkZUqGwKhjurJ5JTpAlwAYl0zIYy6MX6ZZjFBtImYmYmYSZh34tCpy0zpw_Ovjndj1qw9Tr3fgYImySf_oncHBikulhWAd-NgivyoXTbePZz96BjE0l_VPrJ_jVL__9-o_wNPBeHhmzk5H397Cs9igVoZ2AJv17cK_Q95S2_dNuP4GKp3q7g
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=Decentralized+Approximate+Newton+Methods+for+Convex+Optimization+on+Networked+Systems&rft.jtitle=IEEE+transactions+on+control+of+network+systems&rft.au=Hejie+Wei&rft.au=Qu%2C+Zhihai&rft.au=Wu%2C+Xuyang&rft.au=Wang%2C+Hao&rft.date=2021-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2372-2533&rft.volume=8&rft.issue=3&rft.spage=1489&rft_id=info:doi/10.1109%2FTCNS.2021.3070663&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2325-5870&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2325-5870&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2325-5870&client=summon