A stochastic primal–dual algorithm for composite optimization with a linear operator

This paper introduces a stochastic primal–dual algorithm tailored for solving optimization problems involving the sum of three functions with a linear operator. Additionally, we conduct a comprehensive analysis of the convergence of our proposed algorithm within a generally convex framework. Our stu...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications Vol. 267; p. 126021
Main Authors: Wen, Meng, Zhang, Yongqiang, Tang, Yuchao, Cui, Angang, Peng, Jigen
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.04.2025
Subjects:
ISSN:0957-4174
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This paper introduces a stochastic primal–dual algorithm tailored for solving optimization problems involving the sum of three functions with a linear operator. Additionally, we conduct a comprehensive analysis of the convergence of our proposed algorithm within a generally convex framework. Our study includes numerical experiments focusing on fused logistic regression and graph-guided regularized logistic regression problems. The results demonstrate that our algorithm outperforms other state-of-the-art methods in terms of efficiency and consistency. •Design a new stochastic primal–dual algorithm for solving Non-smooth optimization problems.•Conduct a comprehensive analysis of the convergence of our proposed algorithm.•Illustrate the efficiency of our proposed algorithm through some numerical example.
AbstractList This paper introduces a stochastic primal–dual algorithm tailored for solving optimization problems involving the sum of three functions with a linear operator. Additionally, we conduct a comprehensive analysis of the convergence of our proposed algorithm within a generally convex framework. Our study includes numerical experiments focusing on fused logistic regression and graph-guided regularized logistic regression problems. The results demonstrate that our algorithm outperforms other state-of-the-art methods in terms of efficiency and consistency. •Design a new stochastic primal–dual algorithm for solving Non-smooth optimization problems.•Conduct a comprehensive analysis of the convergence of our proposed algorithm.•Illustrate the efficiency of our proposed algorithm through some numerical example.
ArticleNumber 126021
Author Tang, Yuchao
Cui, Angang
Zhang, Yongqiang
Peng, Jigen
Wen, Meng
Author_xml – sequence: 1
  givenname: Meng
  orcidid: 0000-0002-9911-3245
  surname: Wen
  fullname: Wen, Meng
  email: wen5495688@163.com
  organization: School of Science, Xi’an Polytechnic University, Xi’an, 710048, PR China
– sequence: 2
  givenname: Yongqiang
  surname: Zhang
  fullname: Zhang, Yongqiang
  organization: College of Materials Science and Engineering, Xi’an Shiyou University, Xi’an, 710065, PR China
– sequence: 3
  givenname: Yuchao
  surname: Tang
  fullname: Tang, Yuchao
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, 510006, PR China
– sequence: 4
  givenname: Angang
  surname: Cui
  fullname: Cui, Angang
  organization: School of Mathematics and Statistics, Yulin University, Yulin, 719000, PR China
– sequence: 5
  givenname: Jigen
  surname: Peng
  fullname: Peng, Jigen
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, 510006, PR China
BookMark eNp9kDtOAzEQhl0EiSRwASpfYJfxY9esRBNFvKRINEBrOfaEONpdR7Yhgoo7cENOkg2hpppi5hv9_zchoz70SMgFg5IBqy83JaadKTlwWTJeA2cjMoamUoVkSp6SSUobAKYA1Ji8zGjKwa5Nyt7SbfSdaX--vt2baalpX0P0ed3RVYjUhm4bks9Iwzb7zn-a7ENPd8MBNbT1PZo4rDCaHOIZOVmZNuH535yS59ubp_l9sXi8e5jPFoXlFcsFSuQGlFGicjV3ShhVN8IsG6ucqBqERkLFG-6WUAnBJcJVoyzIZS1MhU6KKeHHvzaGlCKu9G-F-KEZ6IMNvdEHG_pgQx9tDND1EcIh2bvHqJP12Ft0PqLN2gX_H74HMH9uNQ
Cites_doi 10.1137/130919362
10.1137/110848876
10.1109/TAC.2023.3301289
10.1109/TSP.2023.3250839
10.1214/aoms/1177729586
10.1007/s10107-010-0434-y
10.1007/s10915-018-0680-3
10.1137/070704277
10.1111/j.1467-9868.2005.00490.x
ContentType Journal Article
Copyright 2024 Elsevier Ltd
Copyright_xml – notice: 2024 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.eswa.2024.126021
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_eswa_2024_126021
S0957417424028884
GroupedDBID --K
--M
.DC
.~1
0R~
13V
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
9JO
AAAKF
AABNK
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AAXKI
AAXUO
AAYFN
ABBOA
ABFNM
ABJNI
ABMAC
ABMVD
ABUCO
ACDAQ
ACGFS
ACHRH
ACNTT
ACRLP
ACZNC
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AFJKZ
AFKWA
AFTJW
AGHFR
AGUBO
AGUMN
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALEQD
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ANKPU
AOUOD
APLSM
AXJTR
BJAXD
BKOJK
BLXMC
BNSAS
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
IHE
J1W
JJJVA
KOM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
ROL
RPZ
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SSB
SSD
SSL
SST
SSV
SSZ
T5K
TN5
~G-
29G
9DU
AAAKG
AAQXK
AATTM
AAYWO
AAYXX
ABKBG
ABUFD
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
LG9
LY1
LY7
M41
R2-
SBC
SET
WUQ
XPP
ZMT
~HD
ID FETCH-LOGICAL-c251t-e4e2a07a735d62d73a7693ab9c7d359e09405292db053324e0897c04b63a5ed43
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001392839400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0957-4174
IngestDate Sat Nov 29 03:07:47 EST 2025
Sat Feb 15 15:52:43 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords 90C25
Three-operator splitting
49M29
65K10
Stochastic algorithm
49M27
47H05
Compositely optimization
Primal–dual algorithm
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c251t-e4e2a07a735d62d73a7693ab9c7d359e09405292db053324e0897c04b63a5ed43
ORCID 0000-0002-9911-3245
ParticipantIDs crossref_primary_10_1016_j_eswa_2024_126021
elsevier_sciencedirect_doi_10_1016_j_eswa_2024_126021
PublicationCentury 2000
PublicationDate 2025-04-01
2025-04-00
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationTitle Expert systems with applications
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Nemirovski, Juditsky, Lan (b13) 2009; 19
Zhong, W., & Kwok, J. (2014b). Fast stochastic alternating direction method of multipliers. In
Zhao, Cevher (b23) 2018
Guo, Shi, Sf (b7) 2023; 69
Zhong, W., & Kwok, J. (2014a). Accelerated stochastic gradient method for composite regularization. In
Chen, Lan, Ouyang (b4) 2014; 24
Robbins, Monro (b15) 1951; 22
Tibshirani, Saunders, Rosset (b19) 2005; 67
Yan (b21) 2018; 76
Guo, Shi, Cao (b6) 2023; 71
Scheinberg, K., Ma, S., & Goldfarb, D. (2010). Sparse inverse covariance selection via alternating linearization methods. In
Kushner, Yin (b11) 2003
Suzuki, T. (2013). Dual averaging and proximal gradient descent for online alternating direction multiplier method. In
Boyd, Vandenberghe (b3) 2004
(pp. 620–628).
(pp. 69–77).
Azadi, S., & Sra, S. (2014). Towards an optimal stochastic alternating direction method of multipliers. In
(pp. 80–88).
(pp. 46–54).
Ghadimi, Lan (b5) 2013; 23
James, Paulson, Rusmevichientong (b10) 2013
Hazan, Kale (b8) 2014; 15
Rosasco, Villa, Vu (b16) 2014
Yurtsever, A., Vu, B. C., & Cevher, V. (2016). Stochastic three-composite convex minimization. In
(pp. 781–789).
Ouyang, H., He, N., Tran, L., et al. (2013). Stochastic alternating direction method of multipliers. In
(pp. 392–400).
(pp. 4329–4337).
(pp. 1086–1094).
(pp. 2101–2109).
Lan (b12) 2012; 133
Vapnik (b20) 2000
Atchadé, Fort, Moulines (b1) 2017; 18
Hu, C., Pan, W., & Kwok, J. T. (2009). Accelerated gradient methods for stochastic optimization and online learning. In
Zhao, P., Yang, J., Zhang, T., et al. (2015). Adaptive stochastic alternating direction method of multipliers. In
Boyd (10.1016/j.eswa.2024.126021_b3) 2004
Atchadé (10.1016/j.eswa.2024.126021_b1) 2017; 18
10.1016/j.eswa.2024.126021_b2
James (10.1016/j.eswa.2024.126021_b10) 2013
Ghadimi (10.1016/j.eswa.2024.126021_b5) 2013; 23
Hazan (10.1016/j.eswa.2024.126021_b8) 2014; 15
Guo (10.1016/j.eswa.2024.126021_b6) 2023; 71
Zhao (10.1016/j.eswa.2024.126021_b23) 2018
Kushner (10.1016/j.eswa.2024.126021_b11) 2003
Chen (10.1016/j.eswa.2024.126021_b4) 2014; 24
10.1016/j.eswa.2024.126021_b14
Lan (10.1016/j.eswa.2024.126021_b12) 2012; 133
10.1016/j.eswa.2024.126021_b17
10.1016/j.eswa.2024.126021_b18
Nemirovski (10.1016/j.eswa.2024.126021_b13) 2009; 19
Guo (10.1016/j.eswa.2024.126021_b7) 2023; 69
Vapnik (10.1016/j.eswa.2024.126021_b20) 2000
Yan (10.1016/j.eswa.2024.126021_b21) 2018; 76
Robbins (10.1016/j.eswa.2024.126021_b15) 1951; 22
10.1016/j.eswa.2024.126021_b25
10.1016/j.eswa.2024.126021_b26
Rosasco (10.1016/j.eswa.2024.126021_b16) 2014
10.1016/j.eswa.2024.126021_b9
Tibshirani (10.1016/j.eswa.2024.126021_b19) 2005; 67
10.1016/j.eswa.2024.126021_b22
10.1016/j.eswa.2024.126021_b24
References_xml – volume: 71
  start-page: 786
  year: 2023
  end-page: 801
  ident: b6
  article-title: Decentralized inexact proximal gradient method for convex composite optimization
  publication-title: IEEE Transactions on Signal Processing
– volume: 69
  start-page: 2995
  year: 2023
  end-page: 3010
  ident: b7
  article-title: A dual inexact splitting algorithm for distributed convex composite optimization
  publication-title: IEEE Transactions on Automatic Control
– reference: Azadi, S., & Sra, S. (2014). Towards an optimal stochastic alternating direction method of multipliers. In
– reference: (pp. 80–88).
– reference: (pp. 620–628).
– reference: Suzuki, T. (2013). Dual averaging and proximal gradient descent for online alternating direction multiplier method. In
– reference: (pp. 392–400).
– year: 2013
  ident: b10
  article-title: The constrained lasso
– reference: Scheinberg, K., Ma, S., & Goldfarb, D. (2010). Sparse inverse covariance selection via alternating linearization methods. In
– volume: 67
  start-page: 91
  year: 2005
  end-page: 108
  ident: b19
  article-title: Sparsity and smoothness via the fused lasso
  publication-title: Journal of the Royal Statistical Society. Series B. Statistical Methodology
– reference: (pp. 46–54).
– year: 2004
  ident: b3
  article-title: Convex optimization
– volume: 24
  start-page: 1779
  year: 2014
  end-page: 1814
  ident: b4
  article-title: Optimal primal–dual methods for a class of saddle point problems
  publication-title: SIAM Journal on Optimization
– year: 2014
  ident: b16
  publication-title: Convergence of stochastic proximal gradient algorithm
– reference: Zhao, P., Yang, J., Zhang, T., et al. (2015). Adaptive stochastic alternating direction method of multipliers. In
– reference: Hu, C., Pan, W., & Kwok, J. T. (2009). Accelerated gradient methods for stochastic optimization and online learning. In
– start-page: 765
  year: 2018
  end-page: 774
  ident: b23
  article-title: Stochastic three-composite convex minimization with a linear operator
  publication-title: Proceedings of the twenty-first international conference on artificial intelligence and statistics, vol. 84
– year: 2000
  ident: b20
  article-title: The nature of statistical learning theory
– volume: 15
  start-page: 2489
  year: 2014
  end-page: 2512
  ident: b8
  article-title: Beyond the regret minimization barrier: Optimal algorithms for stochastic strongly-convex optimization
  publication-title: Journal of Machine Learning Research
– reference: (pp. 2101–2109).
– volume: 76
  start-page: 1698
  year: 2018
  end-page: 1717
  ident: b21
  article-title: A new primal-dual algorithm for minimizing the sum of three functions with a linear operator
  publication-title: Journal of Scientific Computing
– volume: 18
  start-page: 310
  year: 2017
  end-page: 342
  ident: b1
  article-title: On perturbed proximal gradient algorithms
  publication-title: Journal of Machine Learning Research
– reference: Yurtsever, A., Vu, B. C., & Cevher, V. (2016). Stochastic three-composite convex minimization. In
– reference: (pp. 69–77).
– year: 2003
  ident: b11
  article-title: Stochastic approximation and recursive algorithms and applications
– reference: Zhong, W., & Kwok, J. (2014a). Accelerated stochastic gradient method for composite regularization. In
– volume: 22
  start-page: 400
  year: 1951
  end-page: 407
  ident: b15
  article-title: Stochastic approximation method
  publication-title: Annals of Mathematical Statistics
– reference: (pp. 1086–1094).
– reference: (pp. 781–789).
– reference: Ouyang, H., He, N., Tran, L., et al. (2013). Stochastic alternating direction method of multipliers. In
– reference: Zhong, W., & Kwok, J. (2014b). Fast stochastic alternating direction method of multipliers. In
– volume: 19
  start-page: 1574
  year: 2009
  end-page: 1609
  ident: b13
  article-title: Robust stochastic approximation approach to stochastic programming
  publication-title: SIAM Journal on Optimization
– volume: 23
  start-page: 2061
  year: 2013
  end-page: 2089
  ident: b5
  article-title: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, ii: Shrinking procedures and optimal algorithms
  publication-title: SIAM Journal on Optimization
– volume: 133
  start-page: 365
  year: 2012
  end-page: 397
  ident: b12
  article-title: An optimal method for stochastic composite optimization
  publication-title: Mathematical Programming
– reference: (pp. 4329–4337).
– year: 2014
  ident: 10.1016/j.eswa.2024.126021_b16
– ident: 10.1016/j.eswa.2024.126021_b2
– year: 2004
  ident: 10.1016/j.eswa.2024.126021_b3
– year: 2013
  ident: 10.1016/j.eswa.2024.126021_b10
– volume: 24
  start-page: 1779
  issue: 4
  year: 2014
  ident: 10.1016/j.eswa.2024.126021_b4
  article-title: Optimal primal–dual methods for a class of saddle point problems
  publication-title: SIAM Journal on Optimization
  doi: 10.1137/130919362
– year: 2000
  ident: 10.1016/j.eswa.2024.126021_b20
– volume: 23
  start-page: 2061
  issue: 4
  year: 2013
  ident: 10.1016/j.eswa.2024.126021_b5
  article-title: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, ii: Shrinking procedures and optimal algorithms
  publication-title: SIAM Journal on Optimization
  doi: 10.1137/110848876
– year: 2003
  ident: 10.1016/j.eswa.2024.126021_b11
– ident: 10.1016/j.eswa.2024.126021_b18
– ident: 10.1016/j.eswa.2024.126021_b14
– ident: 10.1016/j.eswa.2024.126021_b22
– ident: 10.1016/j.eswa.2024.126021_b24
– ident: 10.1016/j.eswa.2024.126021_b26
– volume: 69
  start-page: 2995
  issue: 5
  year: 2023
  ident: 10.1016/j.eswa.2024.126021_b7
  article-title: A dual inexact splitting algorithm for distributed convex composite optimization
  publication-title: IEEE Transactions on Automatic Control
  doi: 10.1109/TAC.2023.3301289
– volume: 71
  start-page: 786
  year: 2023
  ident: 10.1016/j.eswa.2024.126021_b6
  article-title: Decentralized inexact proximal gradient method for convex composite optimization
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2023.3250839
– volume: 22
  start-page: 400
  issue: 3
  year: 1951
  ident: 10.1016/j.eswa.2024.126021_b15
  article-title: Stochastic approximation method
  publication-title: Annals of Mathematical Statistics
  doi: 10.1214/aoms/1177729586
– volume: 15
  start-page: 2489
  year: 2014
  ident: 10.1016/j.eswa.2024.126021_b8
  article-title: Beyond the regret minimization barrier: Optimal algorithms for stochastic strongly-convex optimization
  publication-title: Journal of Machine Learning Research
– ident: 10.1016/j.eswa.2024.126021_b9
– volume: 133
  start-page: 365
  issue: 1–2
  year: 2012
  ident: 10.1016/j.eswa.2024.126021_b12
  article-title: An optimal method for stochastic composite optimization
  publication-title: Mathematical Programming
  doi: 10.1007/s10107-010-0434-y
– volume: 18
  start-page: 310
  issue: 1
  year: 2017
  ident: 10.1016/j.eswa.2024.126021_b1
  article-title: On perturbed proximal gradient algorithms
  publication-title: Journal of Machine Learning Research
– ident: 10.1016/j.eswa.2024.126021_b17
– volume: 76
  start-page: 1698
  issue: 3
  year: 2018
  ident: 10.1016/j.eswa.2024.126021_b21
  article-title: A new primal-dual algorithm for minimizing the sum of three functions with a linear operator
  publication-title: Journal of Scientific Computing
  doi: 10.1007/s10915-018-0680-3
– volume: 19
  start-page: 1574
  issue: 4
  year: 2009
  ident: 10.1016/j.eswa.2024.126021_b13
  article-title: Robust stochastic approximation approach to stochastic programming
  publication-title: SIAM Journal on Optimization
  doi: 10.1137/070704277
– ident: 10.1016/j.eswa.2024.126021_b25
– volume: 67
  start-page: 91
  issue: 1
  year: 2005
  ident: 10.1016/j.eswa.2024.126021_b19
  article-title: Sparsity and smoothness via the fused lasso
  publication-title: Journal of the Royal Statistical Society. Series B. Statistical Methodology
  doi: 10.1111/j.1467-9868.2005.00490.x
– start-page: 765
  year: 2018
  ident: 10.1016/j.eswa.2024.126021_b23
  article-title: Stochastic three-composite convex minimization with a linear operator
SSID ssj0017007
Score 2.459745
Snippet This paper introduces a stochastic primal–dual algorithm tailored for solving optimization problems involving the sum of three functions with a linear...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 126021
SubjectTerms Compositely optimization
Primal–dual algorithm
Stochastic algorithm
Three-operator splitting
Title A stochastic primal–dual algorithm for composite optimization with a linear operator
URI https://dx.doi.org/10.1016/j.eswa.2024.126021
Volume 267
WOSCitedRecordID wos001392839400001&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0957-4174
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017007
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV07b9swECZcp0OXNukDTdsEHLoJCiQ-TGk0ihRNhiCDU7iTQEqU48CRXEdOM3Tof-g_7C_p0SRl5Ylm6CIYokzLug_kp7v77hD6CHtGriiPQ6VLEjIj4lJ5pELFy6SkcaxJVKyaTYijo2Q8To97vZ9eC3M5E1WVXF2l8_9qajgHxjbS2UeYu50UTsBnMDocwexw_CfDDwPgc_mpNAWYg7kpJjHzGQ10JbySs0m9mDan56sUQ5NTbhK3dFDD6nHuZJlO8xYYEioXMKRX4fhrfnxTJLlxpaC9SK4TDl_HfGy6sHZ7ZNdL_a2uJt8BoO3IyA8s4R_UbYBkObXJlxN_qfNTEN5Jb_EORxGy2Pbk8Wsvsb043OoZw8uV1UvfWtitj-FsT1_8MNWiCNtbX3y9ivaN3a3NOfTpbGeZmSMzc2R2jidogwieJn20MTzYHx-2USgRWbm9v3MnurL5gTfv5G5i0yEro0303L1l4KFFxxbq6eoleuE7eGC3oL9CX4d4DRZswfLn128DE9zCBANMcAsT3IUJNlbHEluYYA-T1-jk8_7o05fQddoIc-C3TaiZJjISUlBeDEghqDQtMqVKc1FQnmpTZJGTlBTKSLcJ01GSijxiakAl1wWjb1C_qiv9FuFByQzHYZRKycoiVaXOmQbSCMwRqLrYRoF_TNncFlTJ7jfNNuL-SWaOElqqlwEwHvjeu0f9ynv0bI3YD6jfLJZ6Bz3NL5vpxWLXoeIvREGECg
linkProvider Elsevier
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+stochastic+primal%E2%80%93dual+algorithm+for+composite+optimization+with+a+linear+operator&rft.jtitle=Expert+systems+with+applications&rft.au=Wen%2C+Meng&rft.au=Zhang%2C+Yongqiang&rft.au=Tang%2C+Yuchao&rft.au=Cui%2C+Angang&rft.date=2025-04-01&rft.issn=0957-4174&rft.volume=267&rft.spage=126021&rft_id=info:doi/10.1016%2Fj.eswa.2024.126021&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_eswa_2024_126021
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon