Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis

We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions-the agents' sum-utility-plus a nonsmooth (extended-valued) convex one. We propose a general unified algorithmic framework for such a class of problems and provide a convergence...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on signal processing Jg. 69; S. 3555 - 3570
Hauptverfasser: Xu, Jinming, Tian, Ye, Sun, Ying, Scutari, Gesualdo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1053-587X, 1941-0476
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions-the agents' sum-utility-plus a nonsmooth (extended-valued) convex one. We propose a general unified algorithmic framework for such a class of problems and provide a convergence analysis leveraging the theory of operator splitting. Distinguishing features of our scheme are: (i) When each of the agent's functions is strongly convex, the algorithm converges at a linear rate, whose dependence on the agents' functions and network topology is decoupled ; (ii) When the objective function is convex (but not strongly convex), similar decoupling as in (i) is established for the coefficient of the proved sublinear rate. This also reveals the role of function heterogeneity on the convergence rate. (iii) The algorithm can adjust the ratio between the number of communications and computations to achieve a rate (in terms of computations) independent on the network connectivity; and (iv) A by-product of our analysis is a tuning recommendation for several existing (non-accelerated) distributed algorithms yielding provably faster (worst-case) convergence rate for the class of problems under consideration.
AbstractList We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions-the agents' sum-utility-plus a nonsmooth (extended-valued) convex one. We propose a general unified algorithmic framework for such a class of problems and provide a convergence analysis leveraging the theory of operator splitting. Distinguishing features of our scheme are: (i) When each of the agent's functions is strongly convex, the algorithm converges at a linear rate, whose dependence on the agents' functions and network topology is decoupled ; (ii) When the objective function is convex (but not strongly convex), similar decoupling as in (i) is established for the coefficient of the proved sublinear rate. This also reveals the role of function heterogeneity on the convergence rate. (iii) The algorithm can adjust the ratio between the number of communications and computations to achieve a rate (in terms of computations) independent on the network connectivity; and (iv) A by-product of our analysis is a tuning recommendation for several existing (non-accelerated) distributed algorithms yielding provably faster (worst-case) convergence rate for the class of problems under consideration.
Author Sun, Ying
Scutari, Gesualdo
Xu, Jinming
Tian, Ye
Author_xml – sequence: 1
  givenname: Jinming
  surname: Xu
  fullname: Xu, Jinming
  email: jimmyxu@zju.edu.cn
  organization: College of Control Science and Engineering, Zhejiang University, Hangzhou, China
– sequence: 2
  givenname: Ye
  orcidid: 0000-0001-9085-6280
  surname: Tian
  fullname: Tian, Ye
  email: tian110@purdue.edu
  organization: School of Industrial Engineering, Purdue University, West-Lafayette, IN, USA
– sequence: 3
  givenname: Ying
  orcidid: 0000-0002-9709-6509
  surname: Sun
  fullname: Sun, Ying
  email: sun578@purdue.edu
  organization: School of Electrical Engineering and Computer Science, The Pennsylvania State University, State College, PA, USA
– sequence: 4
  givenname: Gesualdo
  orcidid: 0000-0002-6453-6870
  surname: Scutari
  fullname: Scutari, Gesualdo
  email: gscutari@purdue.edu
  organization: School of Industrial Engineering, Purdue University, West-Lafayette, IN, USA
BookMark eNp9kEFLw0AQhRepYFu9C14CnlN3ks2m661Uq0Khgi14kbBJJnVrkq27W6X-ere2ePDgZWaY-d4w83qk0-oWCTkHOgCg4mr-9DiIaASDmA55kooj0gXBIKQs5R1f0yQOk2H6fEJ61q4oBcYE75KXG2WdUfnGYRmM6qU2yr02Nqi0Cca6WWurHAaztVON-pJO6fY6WLSqUh6fGNngpzZvgWxLT7cfaJbYFhiMWllvrbKn5LiStcWzQ-6TxeR2Pr4Pp7O7h_FoGhZxkroQgZdQ0FIkIgeQVV5VnEMuuYgSTKXwXeGBFACQ5QwYhQpzjkzGRVpwGvfJ5X7v2uj3DVqXrfTG-CNsFiUJxDzywVN8TxVGW2uwygrlfn5yRqo6A5rtrMy8ldnOyuxgpRfSP8K1UY002_8kF3uJQsRfXDDmZyL-BhtXgj4
CODEN ITPRED
CitedBy_id crossref_primary_10_1109_TCNS_2024_3393668
crossref_primary_10_1002_sta4_70064
crossref_primary_10_1109_TAC_2023_3279901
crossref_primary_10_1109_TSP_2022_3184770
crossref_primary_10_1007_s11590_023_02011_x
crossref_primary_10_1109_TSP_2024_3514676
crossref_primary_10_1109_TAC_2021_3122586
crossref_primary_10_1109_TAC_2024_3524119
crossref_primary_10_1007_s10957_024_02393_7
crossref_primary_10_1109_OJSP_2025_3557332
crossref_primary_10_1109_TAC_2025_3552743
crossref_primary_10_1080_10618600_2024_2431060
crossref_primary_10_1109_TAC_2024_3471854
crossref_primary_10_1007_s10957_022_02061_8
crossref_primary_10_1109_TIT_2023_3267742
crossref_primary_10_1016_j_sigpro_2025_110275
crossref_primary_10_1007_s10957_024_02554_8
crossref_primary_10_1109_TAC_2023_3301289
crossref_primary_10_1109_TNNLS_2022_3208086
crossref_primary_10_1007_s10994_024_06537_8
crossref_primary_10_1109_TSMC_2024_3405453
crossref_primary_10_1109_TSP_2023_3250839
crossref_primary_10_1109_TSIPN_2022_3190743
crossref_primary_10_1109_TSP_2025_3544517
crossref_primary_10_1007_s10107_023_01997_7
crossref_primary_10_1007_s10957_024_02385_7
crossref_primary_10_1109_TAC_2024_3360287
crossref_primary_10_1109_TSIPN_2025_3600766
crossref_primary_10_1109_TSIPN_2022_3203860
crossref_primary_10_1109_TIT_2022_3176253
crossref_primary_10_1109_TNSE_2022_3155287
crossref_primary_10_1007_s10898_022_01221_4
crossref_primary_10_1109_TCE_2024_3506915
crossref_primary_10_1109_TCNS_2024_3354882
crossref_primary_10_1109_TAC_2021_3116116
crossref_primary_10_1109_TAC_2023_3244904
crossref_primary_10_1109_TAC_2023_3327940
crossref_primary_10_1109_TSMC_2025_3565568
crossref_primary_10_3390_e24091278
crossref_primary_10_1016_j_ifacol_2022_07_264
crossref_primary_10_1109_TAC_2022_3173171
crossref_primary_10_1016_j_neunet_2024_106325
crossref_primary_10_1038_s41598_025_90005_3
crossref_primary_10_1109_TSIPN_2023_3290397
Cites_doi 10.1109/CDC40024.2019.9029902
10.1109/TAC.2017.2730481
10.1109/TSP.2018.2875883
10.1007/s10107-018-01357-w
10.1109/TCNS.2017.2698261
10.1109/ALLERTON.2017.8262874
10.1109/TAC.2017.2713046
10.1109/CDC.2012.6425904
10.1109/CAMSAP45676.2019.9022451
10.1137/16M1084316
10.1109/TSIPN.2018.2846183
10.1016/j.sysconle.2004.02.022
10.1109/TAC.2018.2805260
10.1016/j.ifacol.2019.12.181
10.1109/CDC.2015.7402509
10.23919/ACC.2019.8814838
10.1109/TAC.2020.2972824
10.1017/CBO9780511840371
10.1109/TSP.2015.2461520
10.1007/978-1-4419-8853-9
10.1137/14096668X
10.1109/TAC.2020.3009363
10.1109/TSP.2019.2926022
10.1109/LCSYS.2018.2834316
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
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TSP.2021.3086579
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications 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
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
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 1941-0476
EndPage 3570
ExternalDocumentID 10_1109_TSP_2021_3086579
9447939
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation; USA NSF
  grantid: 1719205
  funderid: 10.13039/100000001
– fundername: ARO
  grantid: W911NF1810238
– fundername: National Natural Science Foundation of China; NSF of China
  grantid: 62003302; 62088101; 61922058; U1909207
  funderid: 10.13039/501100001809
– fundername: Fundamental Research Funds for the Central Universities
  grantid: 2020QNA5014
  funderid: 10.13039/501100012226
– fundername: ONR
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
53G
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AJQPL
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c357t-e16d1c0d959b11afbff661ba6925e7a99b19d1c7111e4b41401feb6e4a3c7c603
IEDL.DBID RIE
ISICitedReferencesCount 48
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000673500300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1053-587X
IngestDate Mon Jun 30 10:22:51 EDT 2025
Tue Nov 18 22:21:57 EST 2025
Sat Nov 29 04:10:53 EST 2025
Wed Aug 27 02:23:35 EDT 2025
IsPeerReviewed true
IsScholarly true
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-c357t-e16d1c0d959b11afbff661ba6925e7a99b19d1c7111e4b41401feb6e4a3c7c603
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-9085-6280
0000-0002-6453-6870
0000-0002-9709-6509
PQID 2551362513
PQPubID 85478
PageCount 16
ParticipantIDs proquest_journals_2551362513
crossref_citationtrail_10_1109_TSP_2021_3086579
ieee_primary_9447939
crossref_primary_10_1109_TSP_2021_3086579
PublicationCentury 2000
PublicationDate 20210000
2021-00-00
20210101
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – year: 2021
  text: 20210000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on signal processing
PublicationTitleAbbrev TSP
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 ref35
ref12
p (ref6) 2016; 2
ref15
ref14
ref31
xu (ref25) 0
ref11
ref32
ref10
ref1
ref16
scaman (ref13) 0
ref19
ref18
xu (ref28) 2020
alghunaim (ref17) 2019
nedi? (ref5) 0
asuncion (ref36) 2007
xu (ref2) 0
ref24
ref23
ref26
ref20
ref22
ref21
alghunaim (ref27) 2021; 66
agarwal (ref34) 0
ref29
ref8
ref7
auzinger (ref30) 2011
ref4
ref3
nesterov (ref37) 2004
shamir (ref33) 0
sun (ref9) 2019
References_xml – ident: ref15
  doi: 10.1109/CDC40024.2019.9029902
– ident: ref31
  doi: 10.1109/TAC.2017.2730481
– start-page: 1000
  year: 0
  ident: ref33
  article-title: Communication-efficient distributed optimization using an approximate newton-type method
  publication-title: Proc Int Conf Mach Learn
– year: 2019
  ident: ref17
  article-title: A linearly convergent proximal gradient algorithm for decentralized optimization
  publication-title: Proc Adv Neural Inf Process Syst
– volume: 2
  start-page: 120
  year: 2016
  ident: ref6
  article-title: Next: In-network nonconvex optimization
  publication-title: IEEE Trans Signal Inf Process Netw
– ident: ref29
  doi: 10.1109/TSP.2018.2875883
– ident: ref8
  doi: 10.1007/s10107-018-01357-w
– start-page: 3027
  year: 0
  ident: ref13
  article-title: Optimal algorithms for smooth and strongly convex distributed optimization in networks
  publication-title: Proc 34th Int Conf Mach Learn
– ident: ref7
  doi: 10.1109/TCNS.2017.2698261
– ident: ref24
  doi: 10.1109/ALLERTON.2017.8262874
– start-page: 2381
  year: 0
  ident: ref25
  article-title: Accelerated primal-dual algorithms for distributed smooth convex optimization over networks
  publication-title: Proc 23rd Int Conf Artif Intell Statist
– ident: ref20
  doi: 10.1109/TAC.2017.2713046
– ident: ref16
  doi: 10.1109/CDC.2012.6425904
– ident: ref1
  doi: 10.1109/CAMSAP45676.2019.9022451
– ident: ref10
  doi: 10.1137/16M1084316
– year: 2020
  ident: ref28
  article-title: Distributed algorithms for composite optimization: unified framework and convergence analysis
– start-page: 2309
  year: 0
  ident: ref2
  article-title: A unified algorithmic framework for distributed composite optimization
  publication-title: Proc 59th IEEE Conf Decis Control
– ident: ref14
  doi: 10.1109/TSIPN.2018.2846183
– ident: ref35
  doi: 10.1016/j.sysconle.2004.02.022
– ident: ref19
  doi: 10.1109/TAC.2018.2805260
– start-page: 3950
  year: 0
  ident: ref5
  article-title: Geometrically convergent distributed optimization with uncoordinated step-sizes
  publication-title: Proc Amer Control Conf
– year: 2007
  ident: ref36
  article-title: UCI machine learning repository
– ident: ref26
  doi: 10.1016/j.ifacol.2019.12.181
– ident: ref4
  doi: 10.1109/CDC.2015.7402509
– year: 2011
  ident: ref30
  article-title: Iterative solution of large linear systems
  publication-title: Lecture notes
– start-page: 37
  year: 0
  ident: ref34
  article-title: Fast global convergence rates of gradient methods for high-dimensional statistical recovery
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref23
  doi: 10.23919/ACC.2019.8814838
– ident: ref21
  doi: 10.1109/TAC.2020.2972824
– ident: ref32
  doi: 10.1017/CBO9780511840371
– ident: ref18
  doi: 10.1109/TSP.2015.2461520
– year: 2004
  ident: ref37
  publication-title: Introductory Lectures on Convex Optimization A Basic Course
  doi: 10.1007/978-1-4419-8853-9
– ident: ref3
  doi: 10.1137/14096668X
– ident: ref12
  doi: 10.1109/TSP.2018.2875883
– volume: 66
  year: 2021
  ident: ref27
  article-title: Decentralized proximal gradient algorithms with linear convergence rates
  publication-title: IEEE Trans Autom Control
  doi: 10.1109/TAC.2020.3009363
– ident: ref11
  doi: 10.1109/TSP.2019.2926022
– year: 2019
  ident: ref9
  article-title: Distributed optimization based on gradient-tracking revisited: Enhancing convergence rate via surrogation
– ident: ref22
  doi: 10.1109/LCSYS.2018.2834316
SSID ssj0014496
Score 2.6049955
Snippet We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions-the agents' sum-utility-plus a nonsmooth...
We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions–the agents’ sum-utility–plus a nonsmooth...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 3555
SubjectTerms Algorithms
Convergence
Decoupling
Distributed algorithms
Distributed optimization
Electronic mail
Heterogeneity
linear convergence
Network topologies
Network topology
Operators (mathematics)
Optimization
Signal processing algorithms
Sun
Tuning
Title Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis
URI https://ieeexplore.ieee.org/document/9447939
https://www.proquest.com/docview/2551362513
Volume 69
WOSCitedRecordID wos000673500300001&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: 1941-0476
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014496
  issn: 1053-587X
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5q8aAHX1WsVtmDF8G0SbPJZr0VtXiqBRV6kbDZzGqhTaWv3-9sHkVQBC8hhNkQdjaz3-w8PoArH5UhTyNyVBKlDg_ooqQxDipOIKmbaC_SOdmEGAyi0UgOa3CzqYVBxDz5DNv2No_lpzO9skdlHcntOZDcgi0hwqJWaxMx4Dzn4iK44DtBJEZVSNKVnZfnITmCXa_tE34PbNLWty0o51T5YYjz3aW__7_vOoC9EkWyXqH2Q6hhdgS733oLNuDt3rbEtWxWmLLe5H02Hy8_pgtGIJVZI2CTtZA9kcWYlqWYt4wAqCFIyvpVxhZTWUrS2bqo0URW9TA5htf-w8vdo1NyKTjaD8TSQS9MPe2mMpCJ5ymTGEM7c6JC2Q1QKElPJQkIMn3IE27dLoNJiFz5WujQ9U-gns0yPAXGtYgC7etEu5qTCVAhCUgpjLJBRSWa0KmmN9Zlo3HLdzGJc4fDlTEpJLYKiUuFNOF6M-KzaLLxh2zDKmAjV859E1qVBuPyL1zEXcteQw6e55_9Puocduy7iyOVFtSX8xVewLZeL8eL-WW-wL4AFlTPwg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ZS8QwEB68QH3wFtczD74I1u2RNo1voi6KugqusC9S0nSignZlr9_vpMciKIIvpZQJLZl08k3m-AAOA1SGPI3YUWmcOTyki5LGOKg4gSQ_1V6sC7IJ0W7H3a58mILjSS0MIhbJZ3hib4tYftbTI3tU1pTcngPJaZgNOffdslprEjPgvGDjIsAQOGEsunVQ0pXNzuMDuYK-dxIQgg9t2ta3TahgVflhiov9pbX8vy9bgaUKR7KzUvGrMIX5Gix-6y64Ds8Xtimu5bPCjJ29v_T6b8PXjwEjmMqsGbDpWsjuyWZ8VMWYp4wgqCFQylp1zhZTeUbS-bis0kRWdzHZgKfWZef8yqnYFBwdhGLooBdlnnYzGcrU85RJjaG9OVWR9EMUStJTSQKCjB_ylFvHy2AaIVeBFjpyg02YyXs5bgHjWsShDnSqXc3JCKiIBKQURtmwohINaNbTm-iq1bhlvHhPCpfDlQkpJLEKSSqFNOBoMuKzbLPxh-y6VcBErpr7BuzWGkyq_3CQ-Ja_hlw8L9j-fdQBzF917m6T2-v2zQ4s2PeUByy7MDPsj3AP5vR4-Dbo7xeL7QsNbtMJ
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=Distributed+Algorithms+for+Composite+Optimization%3A+Unified+Framework+and+Convergence+Analysis&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Xu%2C+Jinming&rft.au=Tian%2C+Ye&rft.au=Sun%2C+Ying&rft.au=Scutari%2C+Gesualdo&rft.date=2021&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=69&rft.spage=3555&rft.epage=3570&rft_id=info:doi/10.1109%2FTSP.2021.3086579&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSP_2021_3086579
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon