A Fast Distributed Asynchronous Newton-Based Optimization Algorithm

One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focuses on developing distributed algorithms in a synchronous setting under the presence...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on automatic control Ročník 65; číslo 7; s. 2769 - 2784
Hlavní autoři: Mansoori, Fatemeh, Wei, Ermin
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2020
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 One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focuses on developing distributed algorithms in a synchronous setting under the presence of a central clock, where the agents need to wait for the slowest one to finish the update, before proceeding to the next iterate. Asynchronous distributed algorithms remove the need for a central coordinator, reduce the synchronization wait, and allow some agents to compute faster and execute more iterations. In the asynchronous setting, the only known algorithms for solving this problem could achieve an either linear or sublinear rate of convergence. In this paper, we build upon the existing literature to develop and analyze an asynchronous Newton-based method to solve a penalized version of the problem. We show that this algorithm guarantees almost sure convergence with a global linear and local quadratic rate in expectation. Numerical studies confirm the superior performance of our algorithm against other asynchronous methods.
AbstractList One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focuses on developing distributed algorithms in a synchronous setting under the presence of a central clock, where the agents need to wait for the slowest one to finish the update, before proceeding to the next iterate. Asynchronous distributed algorithms remove the need for a central coordinator, reduce the synchronization wait, and allow some agents to compute faster and execute more iterations. In the asynchronous setting, the only known algorithms for solving this problem could achieve an either linear or sublinear rate of convergence. In this paper, we build upon the existing literature to develop and analyze an asynchronous Newton-based method to solve a penalized version of the problem. We show that this algorithm guarantees almost sure convergence with a global linear and local quadratic rate in expectation. Numerical studies confirm the superior performance of our algorithm against other asynchronous methods.
Author Mansoori, Fatemeh
Wei, Ermin
Author_xml – sequence: 1
  givenname: Fatemeh
  orcidid: 0000-0002-6574-4727
  surname: Mansoori
  fullname: Mansoori, Fatemeh
  email: fatemehmansoori2019@u.northwestern.edu
  organization: Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA
– sequence: 2
  givenname: Ermin
  orcidid: 0000-0002-8035-484X
  surname: Wei
  fullname: Wei, Ermin
  email: ermin.wei@northwestern.edu
  organization: Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA
BookMark eNp9kD1PwzAQhi1UJNrCjsQSiTnBduzEGUOggFTRpcyW4w_qqo2L7QiVX09KKwYGptPp3udO90zAqHOdBuAawQwhWN0t6ybDEFUZrvK8gOUZGCNKWYopzkdgDCFiaYVZcQEmIayHtiAEjUFTJzMRYvJgQ_S27aNWSR32nVx517k-JK_6M7ouvRdhmCx20W7tl4jWdUm9eXfextX2EpwbsQn66lSn4G32uGye0_ni6aWp56nEFYopZcqYtiSKEqgwpZBSjQ0kQhhayBYSIpQRRiupJEFKFogJJaURqFUCY5pPwe1x7867j16HyNeu991wkmOCGEEVK-CQgseU9C4Erw3febsVfs8R5AdVfFDFD6r4SdWAFH8QaePPk9ELu_kPvDmCVmv9e4eVrCJlnn8D2TN5FQ
CODEN IETAA9
CitedBy_id crossref_primary_10_1080_00207179_2021_1970816
crossref_primary_10_1016_j_automatica_2021_110156
crossref_primary_10_1109_TCNS_2021_3070663
crossref_primary_10_1016_j_automatica_2021_109886
crossref_primary_10_1016_j_automatica_2024_111629
crossref_primary_10_1016_j_automatica_2020_109286
crossref_primary_10_1109_TCYB_2020_3011819
crossref_primary_10_1109_TSIPN_2021_3083975
crossref_primary_10_3390_fractalfract8120721
crossref_primary_10_1007_s11431_024_2852_1
crossref_primary_10_1109_TAC_2021_3123244
crossref_primary_10_1109_TAC_2024_3439652
crossref_primary_10_1109_TCNS_2023_3285865
crossref_primary_10_1109_TETCI_2024_3437249
crossref_primary_10_1109_TNNLS_2022_3192346
crossref_primary_10_1109_TSMC_2024_3496488
crossref_primary_10_1109_TSMC_2022_3228780
crossref_primary_10_1109_TAC_2024_3360287
crossref_primary_10_1109_TSP_2023_3240652
crossref_primary_10_1109_MRA_2024_3352852
crossref_primary_10_1109_MRA_2024_3358718
crossref_primary_10_1109_TSIPN_2022_3203860
crossref_primary_10_1016_j_neunet_2023_06_001
crossref_primary_10_1109_TAC_2023_3261465
crossref_primary_10_1109_TASLP_2022_3224256
crossref_primary_10_1109_TSP_2024_3424436
crossref_primary_10_1109_TAC_2023_3244904
crossref_primary_10_1016_j_cam_2024_116250
crossref_primary_10_1016_j_asoc_2024_111976
crossref_primary_10_1109_TPWRS_2021_3056543
crossref_primary_10_1109_TASE_2025_3550740
crossref_primary_10_1109_TAC_2022_3173171
crossref_primary_10_1109_LCSYS_2021_3086388
Cites_doi 10.1109/TAC.2013.2253218
10.1109/TSP.2016.2537261
10.1109/MLSP.2014.6958862
10.1145/1961189.1961199
10.1109/CDC.2009.5400289
10.1109/TSP.2016.2537271
10.1109/JSTSP.2011.2120593
10.1007/s10107-015-0901-6
10.1109/JSTSP.2011.2118740
10.1109/TAC.1986.1104412
10.1109/TAC.2011.2161027
10.1137/S0036144504446096
10.1137/15M1024950
10.1109/TSP.2015.2449255
10.1561/2200000016
10.1007/978-3-642-12598-0_5
10.1109/CDC.2017.8264076
10.1109/TAC.2008.2009515
10.1109/GlobalSIP.2013.6736937
10.1109/TSIPN.2016.2524588
10.1109/TAC.2014.2298712
10.1137/16M1080173
10.1109/TAC.2003.812781
10.1109/JPROC.2010.2052531
10.1109/ACSSC.2016.7869154
10.1017/CBO9780511804441
10.1109/TAC.2015.2512043
10.1109/CDC.2012.6426375
10.1137/130943170
10.1109/TAC.1983.1103183
10.1017/CBO9780511810817
10.1145/984622.984626
10.1109/TSIPN.2017.2695121
10.1137/14096668X
10.1137/1.9780898718003
10.1109/GlobalSIP.2016.7905906
10.1109/TIT.2006.874516
10.1109/CDC.2012.6425904
10.1109/TSP.2013.2254478
10.1109/TAC.2010.2079650
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
7TB
8FD
FR3
JQ2
L7M
L~C
L~D
DOI 10.1109/TAC.2019.2933607
DatabaseName IEEE Xplore (IEEE)
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2523
EndPage 2784
ExternalDocumentID 10_1109_TAC_2019_2933607
8789473
Genre orig-research
GrantInformation_xml – fundername: Defense Advanced Research Projects Agency under Contract Langrange
  grantid: HR-001117S0039
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-c291t-58dffb74d540d255055e2f04aaf56cb044adfafedcdc41dc618adccfa1bda2253
IEDL.DBID RIE
ISICitedReferencesCount 36
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000543961200001&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 10:17:55 EDT 2025
Tue Nov 18 22:43:12 EST 2025
Sat Nov 29 05:40:56 EST 2025
Wed Aug 27 02:38:19 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
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-c291t-58dffb74d540d255055e2f04aaf56cb044adfafedcdc41dc618adccfa1bda2253
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8035-484X
0000-0002-6574-4727
PQID 2418419860
PQPubID 85475
PageCount 16
ParticipantIDs proquest_journals_2418419860
crossref_primary_10_1109_TAC_2019_2933607
ieee_primary_8789473
crossref_citationtrail_10_1109_TAC_2019_2933607
PublicationCentury 2000
PublicationDate 2020-07-01
PublicationDateYYYYMMDD 2020-07-01
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on automatic control
PublicationTitleAbbrev TAC
PublicationYear 2020
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
ref12
jerinkic (ref2) 2017
ref15
ref52
ref11
ref54
ref10
ref17
ref16
ref19
ref18
ref51
ref50
zanella (ref55) 0
ref46
ref45
bertsekas (ref4) 1989; 23
ref47
ref41
ref43
ref49
ref8
cottle (ref14) 1992; 60
ref7
ref9
ref3
xiao (ref53) 0
ref5
ref40
hajinezhad (ref21) 0
ref36
ref31
ref33
ref39
ref38
nedi? (ref32) 2011; 56
tsitsiklis (ref48) 1984
mokhtari (ref30) 2015
ref24
ref23
ref26
ref25
ref20
bof (ref6) 2017
assran (ref1) 2018
ref22
nocedal (ref35) 2006
shamir (ref42) 0; 32
ref28
ref27
polyak (ref37) 1987
mokhtari (ref29) 2015
nesterov (ref34) 2013; 87
nedi? (ref44) 2011; 5
References_xml – ident: ref51
  doi: 10.1109/TAC.2013.2253218
– ident: ref13
  doi: 10.1109/TSP.2016.2537261
– ident: ref19
  doi: 10.1109/MLSP.2014.6958862
– year: 2015
  ident: ref29
  article-title: Network Newton-Part I: Algorithm and convergence
  publication-title: arXiv preprint arXiv 1504 06017
– start-page: 63
  year: 0
  ident: ref53
  article-title: A scheme for robust distributed sensor fusion based on average consensus
  publication-title: Proc 4th Int Symp Inf Process Sens Netw
– ident: ref11
  doi: 10.1145/1961189.1961199
– ident: ref24
  doi: 10.1109/CDC.2009.5400289
– ident: ref12
  doi: 10.1109/TSP.2016.2537271
– year: 2006
  ident: ref35
  publication-title: Nonlinear Equations
– start-page: 3215
  year: 0
  ident: ref21
  article-title: NESTT: A nonconvex primal-dual splitting method for distributed and stochastic optimization
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref28
  doi: 10.1109/JSTSP.2011.2120593
– ident: ref40
  doi: 10.1007/s10107-015-0901-6
– volume: 5
  start-page: 772
  year: 2011
  ident: ref44
  article-title: Distributed asynchronous constrained stochastic optimization
  publication-title: IEEE J Sel Topics Signal Process
  doi: 10.1109/JSTSP.2011.2118740
– ident: ref47
  doi: 10.1109/TAC.1986.1104412
– ident: ref17
  doi: 10.1109/TAC.2011.2161027
– ident: ref20
  doi: 10.1137/S0036144504446096
– ident: ref36
  doi: 10.1137/15M1024950
– ident: ref26
  doi: 10.1109/TSP.2015.2449255
– volume: 60
  year: 1992
  ident: ref14
  publication-title: The Linear Complementarity Problem
– ident: ref9
  doi: 10.1561/2200000016
– ident: ref39
  doi: 10.1007/978-3-642-12598-0_5
– year: 1987
  ident: ref37
  publication-title: Introduction to Optimization
– ident: ref27
  doi: 10.1109/CDC.2017.8264076
– ident: ref33
  doi: 10.1109/TAC.2008.2009515
– ident: ref50
  doi: 10.1109/GlobalSIP.2013.6736937
– ident: ref15
  doi: 10.1109/TSIPN.2016.2524588
– ident: ref25
  doi: 10.1109/TAC.2014.2298712
– ident: ref7
  doi: 10.1137/16M1080173
– year: 2017
  ident: ref6
  article-title: Newton-Raphson consensus under asynchronous and lossy communications for peer-to-peer networks
  publication-title: arXiv preprint arXiv 1707 09562
– year: 1984
  ident: ref48
  article-title: Problems in decentralized decision making and computation
– ident: ref23
  doi: 10.1109/TAC.2003.812781
– year: 2017
  ident: ref2
  article-title: Distributed second order methods with variable number of working nodes
  publication-title: arXiv 1709 01307
– ident: ref16
  doi: 10.1109/JPROC.2010.2052531
– ident: ref45
  doi: 10.1109/ACSSC.2016.7869154
– ident: ref10
  doi: 10.1017/CBO9780511804441
– ident: ref5
  doi: 10.1109/TAC.2015.2512043
– ident: ref46
  doi: 10.1109/CDC.2012.6426375
– ident: ref54
  doi: 10.1137/130943170
– year: 2015
  ident: ref30
  article-title: Network Newton-Part II: Convergence rate and implementation
  publication-title: Arxiv preprint Arxiv 1504 06010
– ident: ref3
  doi: 10.1109/TAC.1983.1103183
– volume: 87
  year: 2013
  ident: ref34
  publication-title: Introductory Lectures on Convex Optimization A Basic Course
– ident: ref22
  doi: 10.1017/CBO9780511810817
– ident: ref38
  doi: 10.1145/984622.984626
– ident: ref52
  doi: 10.1109/TSIPN.2017.2695121
– ident: ref43
  doi: 10.1137/14096668X
– start-page: 5917
  year: 0
  ident: ref55
  article-title: Newton-Raphson consensus for distributed convex optimization
  publication-title: Proc 50th IEEE Conf Decis Control/Eur Control Conf
– volume: 32
  start-page: 1000
  year: 0
  ident: ref42
  article-title: Communication-efficient distributed optimization using an approximate Newton-type method
  publication-title: Proc 31st Int Conf Mach Learn
– ident: ref41
  doi: 10.1137/1.9780898718003
– year: 2018
  ident: ref1
  article-title: Asynchronous subgradient-push
  publication-title: arXiv preprint arXiv 1803 08950
– ident: ref18
  doi: 10.1109/GlobalSIP.2016.7905906
– ident: ref8
  doi: 10.1109/TIT.2006.874516
– ident: ref49
  doi: 10.1109/CDC.2012.6425904
– ident: ref31
  doi: 10.1109/TSP.2013.2254478
– volume: 23
  year: 1989
  ident: ref4
  publication-title: Parallel and Distributed Computation Numerical Methods
– volume: 56
  start-page: 1337
  year: 2011
  ident: ref32
  article-title: Asynchronous broadcast-based optimization over a network
  publication-title: IEEE Trans Autom Control
  doi: 10.1109/TAC.2010.2079650
SSID ssj0016441
Score 2.543574
Snippet One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2769
SubjectTerms Agents and autonomous systems
Algorithms
Approximation algorithms
asynchronous algorithms
Clocks
Convergence
Delays
Linear programming
network analysis and control
Optimization
optimization algorithms
Symmetric matrices
Synchronism
Title A Fast Distributed Asynchronous Newton-Based Optimization Algorithm
URI https://ieeexplore.ieee.org/document/8789473
https://www.proquest.com/docview/2418419860
Volume 65
WOSCitedRecordID wos000543961200001&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 Electronic Library (IEL)
  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/eLvHCXMwlV1LS8NAEB7a4kEPvqpYrZKDF8G0eWyS3WOsFg9SPVToLWx2drXQhzSp4L93N0lDQRG8JbALy2zmlZn5PoBrisxFStF2HK5sEiKzU59Qm-tTew4PeVrizD5FoxGdTNhLA27rWRgpZdF8Jnvmsajl41Ksza-yPo0oI5HfhGYUheWsVl0xMH69tLpagT1alyQd1h_HA9PDxXratfmhIY7dckEFp8oPQ1x4l-HB_851CPtVFGnF5bUfQUMujmFvC1uwDYPYGvIst-4NMq4htZJoxdnXQhg0XJ3uW9q8GfrgO-3G0HrWlmNejWRa8extuZrm7_MTeB0-jAePdsWYYAuPubkdUFQqjQjqOAw9k3wE0lMO4VwFoUgdQjgqriQKFMRFEbqUoxCKuylyrdn-KbQWy4U8A0ua1xB56gecRGby3GOKc6ojhFQQknagvxFiIio4ccNqMUuKtMJhiRZ7YsSeVGLvwE2946OE0vhjbduIuV5XSbgD3c09JZWuZYmOQShxGQ2d8993XcCuZ7Lkosm2C618tZaXsCM-82m2uio-o29YYcYq
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB58gXrwLa7PHrwI1u0jbZNjXV0U19XDCt5KmklU0F3ZrYL_3kxbi6AI3lpIIEw6r87M9wEcchQ-co6u50njshiFm4eMu9KeOvBkLPMKZ7aX9Pv8_l7cTsFxMwujtS6bz_QJPZa1fBypN_pV1uYJFywJp2GWmLOialqrqRmQZ6_srlXhgDdFSU-0B2mHurjEiXVuYUzUsd-cUMmq8sMUl_6lu_y_k63AUh1HOml18aswpYdrsPgNXXAdOqnTlZPCOSNsXKK10uikk4-hIjxcm_A71sARgfCpdWTo3Fjb8VIPZTrp88No_FQ8vmzAXfd80Llwa84EVwXCL9yIozF5wtBGYhhQ-hHpwHhMShPFKvcYk2ik0ahQMR9V7HOJShnp5yitboebMDMcDfUWOJpeY5R5GEmW0Ox5IIyU3MYIuWIsb0H7S4iZqgHFidfiOSsTC09kVuwZiT2rxd6Co2bHawWm8cfadRJzs66WcAt2v-4pq7VtktkohDNf8Njb_n3XAcxfDK57We-yf7UDCwHlzGXL7S7MFOM3vQdz6r14moz3y0_qE9tByXU
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+Fast+Distributed+Asynchronous+Newton-Based+Optimization+Algorithm&rft.jtitle=IEEE+transactions+on+automatic+control&rft.au=Mansoori%2C+Fatemeh&rft.au=Wei%2C+Ermin&rft.date=2020-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9286&rft.eissn=1558-2523&rft.volume=65&rft.issue=7&rft.spage=2769&rft_id=info:doi/10.1109%2FTAC.2019.2933607&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