An Edge-based Stochastic Proximal Gradient Algorithm for Decentralized Composite Optimization

This paper investigates decentralized composite optimization problems involving a common non-smooth regularization term over an undirected and connected network. In the same situation, there exist lots of gradient-based proximal distributed methods, but most of them are only sublinearly convergent....

Full description

Saved in:

Bibliographic Details
Published in:	International journal of control, automation, and systems Vol. 19; no. 11; pp. 3598 - 3610
Main Authors:	Zhang, Ling, Yan, Yu, Wang, Zheng, Li, Huaqing
Format:	Journal Article
Language:	English
Published:	Bucheon / Seoul Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers 01.11.2021 Springer Nature B.V 제어·로봇·시스템학회
Subjects:	Algorithms Control Convergence Cost function Engineering Machine learning Mechatronics Optimization Performance degradation Regular Papers Regularization Robotics 제어계측공학 proximal-gradient method Decentralized composite optimization machine learning stochastic averaging gradient linear convergence
ISSN:	1598-6446, 2005-4092
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	This paper investigates decentralized composite optimization problems involving a common non-smooth regularization term over an undirected and connected network. In the same situation, there exist lots of gradient-based proximal distributed methods, but most of them are only sublinearly convergent. The proof of linear convergence for this series of algorithms is extremely difficult. To set up the problem, we presume all networked agents use the same non-smooth regularization term, which is the circumstance for most machine learning to implement based on centralized optimization. For this scenario, most existing proximal-gradient algorithms trend to ignore the cost of gradient evaluations, which results in degraded performance. To tackle this problem, we further set the local cost function to the average of a moderate amount of local cost subfunctions and develop an edge-based stochastic proximal gradient algorithm (SPG-Edge) by employing local unbiased stochastic averaging gradient method. When the non-smooth term does not exist, the proposed algorithm could be extended to some notable primal-dual domain algorithms, such as EXTRA and DIGing. Finally, we provide a simplified proof of linear convergence and conduct numerical experiments to illustrate the validity of theoretical results.
AbstractList	This paper investigates decentralized composite optimization problems involving a common non-smooth regularization term over an undirected and connected network. In the same situation, there exist lots of gradientbased proximal distributed methods, but most of them are only sublinearly convergent. The proof of linear convergence for this series of algorithms is extremely difficult. To set up the problem, we presume all networked agents use the same non-smooth regularization term, which is the circumstance for most machine learning to implement based on centralized optimization. For this scenario, most existing proximal-gradient algorithms trend to ignore the cost of gradient evaluations, which results in degraded performance. To tackle this problem, we further set the local cost function to the average of a moderate amount of local cost subfunctions and develop an edge-based stochastic proximal gradient algorithm (SPG-Edge) by employing local unbiased stochastic averaging gradient method. When the non-smooth term does not exist, the proposed algorithm could be extended to some notable primal-dual domain algorithms, such as EXTRA and DIGing. Finally, we provide a simplified proof of linear convergence and conduct numerical experiments to illustrate the validity of theoretical results. KCI Citation Count: 2 This paper investigates decentralized composite optimization problems involving a common non-smooth regularization term over an undirected and connected network. In the same situation, there exist lots of gradient-based proximal distributed methods, but most of them are only sublinearly convergent. The proof of linear convergence for this series of algorithms is extremely difficult. To set up the problem, we presume all networked agents use the same non-smooth regularization term, which is the circumstance for most machine learning to implement based on centralized optimization. For this scenario, most existing proximal-gradient algorithms trend to ignore the cost of gradient evaluations, which results in degraded performance. To tackle this problem, we further set the local cost function to the average of a moderate amount of local cost subfunctions and develop an edge-based stochastic proximal gradient algorithm (SPG-Edge) by employing local unbiased stochastic averaging gradient method. When the non-smooth term does not exist, the proposed algorithm could be extended to some notable primal-dual domain algorithms, such as EXTRA and DIGing. Finally, we provide a simplified proof of linear convergence and conduct numerical experiments to illustrate the validity of theoretical results.
Author	Li, Huaqing Zhang, Ling Yan, Yu Wang, Zheng
Author_xml	– sequence: 1 givenname: Ling surname: Zhang fullname: Zhang, Ling organization: Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University – sequence: 2 givenname: Yu orcidid: 0000-0002-5015-0803 surname: Yan fullname: Yan, Yu email: yanyu_nice@163.com organization: Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University – sequence: 3 givenname: Zheng surname: Wang fullname: Wang, Zheng organization: School of Electrical Engineering and Telecommunications, University of New South Wales – sequence: 4 givenname: Huaqing orcidid: 0000-0001-6310-8965 surname: Li fullname: Li, Huaqing email: huaqingli@swu.edu.cn organization: Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University
BackLink	https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002768067$$DAccess content in National Research Foundation of Korea (NRF)
BookMark	eNp9kE1rFTEUhoO04G31B7gbcOUiepLJx2R5uba1UKjYdllCJh-3aedOrkkK2l9v2hEEQVcHXt7nnMNzhA7mNHuE3hH4SADkp0Io5xwDBQxs6LF6hVYUgGMGih6gFeFqwIIx8RodlXIPIARVcoVu13N34rYej6Z4113VZO9MqdF2X3P6EXdm6s6ycdHPtVtP25Rjvdt1IeXus7ctzGaKTw3cpN0-lVh9d7mvcRefTI1pfoMOg5mKf_t7HqOb05PrzRd8cXl2vllfYNtzqNg7b6hxgfQQgnG9DH1Q0sograUcWK9AMDM6y4QfR2JaKq13oxGBCeFof4w-LHvnHPSDjTqZ-DK3ST9kvf52fa7VIBkM0Lrvl-4-p--PvlR9nx7z3N7TlA-KKKp431pkadmcSsk-6H1uNvJPTUA_G9eLcd2M62fjWjVG_sXYWF88NE1x-i9JF7K0K_PW5z8__Rv6BSyFmIQ
CitedBy_id	crossref_primary_10_1007_s12555_024_0424_0 crossref_primary_10_1007_s12555_023_0211_3
Cites_doi	10.1561/2200000051 10.1109/TSP.2013.2254478 10.1109/TSP.2016.2617829 10.1109/TSP.2010.2055862 10.1109/TSP.2010.2047721 10.1137/16M1084316 10.1016/j.asoc.2018.08.044 10.1109/TKDE.2012.191 10.1109/TSP.2014.2367458 10.1007/s12555-017-0717-7 10.1007/s12555-018-0191-x 10.1007/s12555-018-9543-9 10.1109/TSP.2015.2461520 10.1109/TAC.2017.2713046 10.1109/TSP.2007.906734 10.1109/TNSE.2019.2933177 10.1137/14096668X 10.1109/TSP.2014.2304432 10.1109/TRO.2017.2686441 10.1109/TSP.2018.2875898 10.1109/TAC.1986.1104412
ContentType	Journal Article
Copyright	ICROS, KIEE and Springer 2021 ICROS, KIEE and Springer 2021.
Copyright_xml	– notice: ICROS, KIEE and Springer 2021 – notice: ICROS, KIEE and Springer 2021.
DBID	AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D ACYCR
DOI	10.1007/s12555-020-0483-9
DatabaseName	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 Korean Citation Index
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
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2005-4092
EndPage	3610
ExternalDocumentID	oai_kci_go_kr_ARTI_9874080 10_1007_s12555_020_0483_9
GroupedDBID	-EM .UV 06D 0R~ 0VY 1N0 203 29J 29~ 2KG 2LR 2VQ 30V 3V. 4.4 406 408 40D 5GY 5VS 67Z 7WY 8FE 8FG 8FL 96X 9ZL AACDK AAHNG AAIAL AAJBT AAJKR AAKPC AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH AAZMS ABAKF ABDZT ABECU ABFTD ABFTV ABJNI ABJOX ABKCH ABMQK ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABUWG ABXPI ACAOD ACDTI ACGFS ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACOKC ACPIV ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AEPYU AESKC AETCA AEVLU AEXYK AFBBN AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF AMYQR ANMIH AOCGG ARAPS ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC BA0 BENPR BEZIV BGLVJ BGNMA BPHCQ CAG CCPQU COF CSCUP DBRKI DDRTE DNIVK DPUIP DU5 DWQXO EBLON EBS EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRJ FRNLG FRRFC FSGXE FYJPI GGCAI GGRSB GJIRD GNUQQ GQ6 GQ7 GROUPED_ABI_INFORM_COMPLETE GW5 H13 HCIFZ HF~ HG6 HLICF HMJXF HRMNR HVGLF HZ~ IKXTQ IWAJR IXC IXD I~X J-C J0Z JBSCW JZLTJ K60 K6V K6~ K7- KOV KVFHK LLZTM M0C M0N M4Y MA- NPVJJ NQJWS NU0 O9- O9J P62 P9P PQBIZ PQBZA PQQKQ PROAC PT4 Q2X R9I ROL RSV S1Z S27 S3B SDH SEG SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE T13 TDB TSG U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W48 WK8 Z45 Z7R Z7X Z7Z Z83 Z88 ZMTXR ~A9 AAPKM AAYXX ABDBE ABFSG ABJCF ABRTQ ACSTC AEZWR AFDZB AFFHD AFHIU AFOHR AHPBZ AHWEU AIXLP ATHPR CITATION M7S PHGZM PHGZT PQGLB PTHSS 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D ACYCR PMFND
ID	FETCH-LOGICAL-c350t-edea2adf130ffad37f3f97c7f7cc250439064abdc46ebb1acc27cedba6f466d23
IEDL.DBID	RSV
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000692086100024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1598-6446
IngestDate	Thu May 29 05:21:49 EDT 2025 Wed Sep 17 23:59:56 EDT 2025 Sat Nov 29 01:37:42 EST 2025 Tue Nov 18 21:55:34 EST 2025 Fri Feb 21 02:47:46 EST 2025
IsPeerReviewed	false
IsScholarly	true
Issue	11
Keywords	proximal-gradient method Decentralized composite optimization machine learning stochastic averaging gradient linear convergence
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c350t-edea2adf130ffad37f3f97c7f7cc250439064abdc46ebb1acc27cedba6f466d23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 http://link.springer.com/article/10.1007/s12555-020-0483-9
ORCID	0000-0002-5015-0803 0000-0001-6310-8965
PQID	2589192953
PQPubID	326316
PageCount	13
ParticipantIDs	nrf_kci_oai_kci_go_kr_ARTI_9874080 proquest_journals_2589192953 crossref_primary_10_1007_s12555_020_0483_9 crossref_citationtrail_10_1007_s12555_020_0483_9 springer_journals_10_1007_s12555_020_0483_9
PublicationCentury	2000
PublicationDate	2021-11-01
PublicationDateYYYYMMDD	2021-11-01
PublicationDate_xml	– month: 11 year: 2021 text: 2021-11-01 day: 01
PublicationDecade	2020
PublicationPlace	Bucheon / Seoul
PublicationPlace_xml	– name: Bucheon / Seoul – name: Heidelberg
PublicationSubtitle	IJCAS
PublicationTitle	International journal of control, automation, and systems
PublicationTitleAbbrev	Int. J. Control Autom. Syst
PublicationYear	2021
Publisher	Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers Springer Nature B.V 제어·로봇·시스템학회
Publisher_xml	– name: Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers – name: Springer Nature B.V – name: 제어·로봇·시스템학회
References	Boulkaibet, Belarbi, Bououden, Chadli, Marwala (CR18) 2018; 73 Smith, Forte, Chenxin, Takac, Jordan, Jaggi (CR10) 2018; 18 Wang, Zheng, Li (CR23) 2020; 18 CR12 CR11 Yan, Sundaram, Vishwanathan, Qi (CR6) 2013; 25 Chang, Hong, Wang (CR22) 2015; 63 Sayed (CR8) 2014; 7 Nedic, Olshevsky, Shi (CR1) 2017; 27 Shi, Ling, Yuan, Wu, Yin (CR5) 2014; 62 Schizas, Ribeiro, Giannakis (CR3) 2008; 56 Aybat, Wang, Lin, Ma (CR4) 2018; 63 Mota, Xavier, Aguiar (CR16) 2013; 61 Ling, Tian (CR20) 2010; 58 Mokhtari, Ling, Ribeiro (CR14) 2016; 65 Sui, Duan, Hou, Zhang (CR26) 2019; 17 CR28 Wang, Li (CR25) 2020; 7 CR24 Seaman, Bach, Bubeck, Lee, Massoulie (CR15) 2017; 70 Shi, Ling, Wu, Yin (CR7) 2015; 63 Yuan, Ying, Zhao, Sayed (CR9) 2019; 67 Tsitsiklis, Bertsekas, Athans (CR19) 1986; 31 Safavi, Khan (CR21) 2017; 33 Zhang, Gong, Yang, Chen (CR27) 2019; 17 Shi, Ling, Wu, Yin (CR2) 2015; 25 Mateos, Bazerque, Giannakis (CR17) 2010; 58 Mokhtari, Ribeiro (CR13) 2016; 17 N Aybat (483_CR4) 2018; 63 Z Wang (483_CR23) 2020; 18 Q Ling (483_CR20) 2010; 58 G Mateos (483_CR17) 2010; 58 A H Sayed (483_CR8) 2014; 7 J Tsitsiklis (483_CR19) 1986; 31 483_CR12 K Yuan (483_CR9) 2019; 67 I Schizas (483_CR3) 2008; 56 I Boulkaibet (483_CR18) 2018; 73 A Nedic (483_CR1) 2017; 27 483_CR11 A Mokhtari (483_CR13) 2016; 17 S Safavi (483_CR21) 2017; 33 W Shi (483_CR5) 2014; 62 J Mota (483_CR16) 2013; 61 W S Sui (483_CR26) 2019; 17 W Shi (483_CR7) 2015; 63 V Smith (483_CR10) 2018; 18 F Yan (483_CR6) 2013; 25 A Mokhtari (483_CR14) 2016; 65 Q Zhang (483_CR27) 2019; 17 W Shi (483_CR2) 2015; 25 K Seaman (483_CR15) 2017; 70 483_CR24 T-H Chang (483_CR22) 2015; 63 483_CR28 Z Wang (483_CR25) 2020; 7
References_xml	– volume: 7 start-page: 311 issue: 4–5 year: 2014 end-page: 801 ident: CR8 article-title: Adaptation, learning, and optimization over networks publication-title: Foundations and Trends in Machine Learning doi: 10.1561/2200000051 – volume: 61 start-page: 2718 issue: 10 year: 2013 end-page: 2723 ident: CR16 article-title: DADMM: A communication-efficient distributed algorithm for separable optimization publication-title: IEEE Transactions on Signal Process doi: 10.1109/TSP.2013.2254478 – ident: CR12 – volume: 65 start-page: 146 issue: 1 year: 2016 end-page: 161 ident: CR14 article-title: Network Newton distributed optimization methods publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2016.2617829 – volume: 58 start-page: 5262 issue: 10 year: 2010 end-page: 5276 ident: CR17 article-title: Distributed sparse linear regression publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2010.2055862 – volume: 58 start-page: 3816 issue: 7 year: 2010 end-page: 3827 ident: CR20 article-title: Decentralized sparse signal recovery for compressive sleeping wireless sensor networks publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2010.2047721 – volume: 27 start-page: 2597 issue: 4 year: 2017 end-page: 2633 ident: CR1 article-title: Achieving geometric convergence for distributed optimization over time-varying graphs publication-title: SIAM Journal on Optimization doi: 10.1137/16M1084316 – volume: 73 start-page: 572 year: 2018 end-page: 590 ident: CR18 article-title: An adaptive fuzzy predictive control of nonlinear processes based on multi-kernel least squares support vector regression publication-title: Applied Soft Computing doi: 10.1016/j.asoc.2018.08.044 – volume: 25 start-page: 2483 issue: 11 year: 2013 end-page: 2493 ident: CR6 article-title: Distributed autonomous online learning: Regrets and intrinsic privacy-preserving properties publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2012.191 – volume: 70 start-page: 3027 year: 2017 end-page: 3036 ident: CR15 article-title: Optimal algorithms for smooth and strongly convex distributed optimization in networks publication-title: Proceedings of the 34th International Conference on Machine Learning – volume: 63 start-page: 482 issue: 2 year: 2015 end-page: 497 ident: CR22 article-title: Multi-agent distributed optimization via inexact consensus ADMM publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2014.2367458 – volume: 17 start-page: 1117 issue: 6 year: 2019 end-page: 1130 ident: CR26 article-title: Distributed fixed-time attitude synchronization control for multiple rigid spacecraft publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-017-0717-7 – volume: 17 start-page: 1177 issue: 5 year: 2019 end-page: 1183 ident: CR27 article-title: Distributed convex optimization for flocking of nonlinear multi-agent systems publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-018-0191-x – volume: 18 start-page: 2534 issue: 10 year: 2020 end-page: 2542 ident: CR23 article-title: Distributed optimization over general directed networks with random sleep scheme publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-018-9543-9 – volume: 63 start-page: 6013 issue: 22 year: 2015 end-page: 6023 ident: CR7 article-title: A proximal gradient algorithm for decentralized composite optimization publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2015.2461520 – volume: 63 start-page: 5 issue: 1 year: 2018 end-page: 20 ident: CR4 article-title: Distributed linearized alternating direction method of multipliers for composite convex consensus optimization publication-title: IEEE Transactions on Automatic Control doi: 10.1109/TAC.2017.2713046 – volume: 56 start-page: 350 issue: 1 year: 2008 end-page: 364 ident: CR3 article-title: Consensus in ad hoc WSNs with noisy links-part I: Distributed estimation of deterministic signals publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2007.906734 – volume: 7 start-page: 1421 issue: 3 year: 2020 end-page: 1430 ident: CR25 article-title: Edge-based stochastic gradient algorithm for distributed optimization publication-title: IEEE Transactions on Network Science and Engineering doi: 10.1109/TNSE.2019.2933177 – volume: 25 start-page: 944 issue: 2 year: 2015 end-page: 966 ident: CR2 article-title: EXTRA: An exact first-order algorithm for decentralized consensus optimization publication-title: SIAM Journal on Optimization doi: 10.1137/14096668X – volume: 18 start-page: 8590 issue: 1 year: 2018 end-page: 8638 ident: CR10 article-title: CoCoA: A general framework for communication efficient distributed optimization publication-title: Journal of Machine Learning Research – volume: 62 start-page: 1750 year: 2014 end-page: 1761 ident: CR5 article-title: On the linear convergence of the ADMM in decentralized consensus optimization publication-title: IEEE Transactions on Signal Process doi: 10.1109/TSP.2014.2304432 – volume: 17 start-page: 1 year: 2016 end-page: 35 ident: CR13 article-title: DSA: Decentralized double stochastic averaging gradient algorithm publication-title: The Journal of Machine Learning Research – volume: 33 start-page: 875 issue: 4 year: 2017 end-page: 888 ident: CR21 article-title: An opportunistic linear-convex algorithm for localization in mobile robot networks publication-title: IEEE Transactions on Robotics doi: 10.1109/TRO.2017.2686441 – ident: CR11 – volume: 67 start-page: 708 issue: 3 year: 2019 end-page: 723 ident: CR9 article-title: Exact diffusion for distributed optimization and learning-Part I: Algorithm development publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2018.2875898 – ident: CR28 – volume: 31 start-page: 803 issue: 9 year: 1986 end-page: 812 ident: CR19 article-title: Distributed asynchronous deterministic and stochastic gradient optimization algorithms publication-title: IEEE Transactions on Automatic Control doi: 10.1109/TAC.1986.1104412 – ident: CR24 – ident: 483_CR28 – volume: 61 start-page: 2718 issue: 10 year: 2013 ident: 483_CR16 publication-title: IEEE Transactions on Signal Process doi: 10.1109/TSP.2013.2254478 – ident: 483_CR24 – volume: 7 start-page: 311 issue: 4–5 year: 2014 ident: 483_CR8 publication-title: Foundations and Trends in Machine Learning doi: 10.1561/2200000051 – volume: 33 start-page: 875 issue: 4 year: 2017 ident: 483_CR21 publication-title: IEEE Transactions on Robotics doi: 10.1109/TRO.2017.2686441 – volume: 67 start-page: 708 issue: 3 year: 2019 ident: 483_CR9 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2018.2875898 – volume: 63 start-page: 482 issue: 2 year: 2015 ident: 483_CR22 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2014.2367458 – ident: 483_CR11 – volume: 18 start-page: 8590 issue: 1 year: 2018 ident: 483_CR10 publication-title: Journal of Machine Learning Research – volume: 27 start-page: 2597 issue: 4 year: 2017 ident: 483_CR1 publication-title: SIAM Journal on Optimization doi: 10.1137/16M1084316 – volume: 17 start-page: 1177 issue: 5 year: 2019 ident: 483_CR27 publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-018-0191-x – volume: 62 start-page: 1750 year: 2014 ident: 483_CR5 publication-title: IEEE Transactions on Signal Process doi: 10.1109/TSP.2014.2304432 – volume: 18 start-page: 2534 issue: 10 year: 2020 ident: 483_CR23 publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-018-9543-9 – volume: 63 start-page: 5 issue: 1 year: 2018 ident: 483_CR4 publication-title: IEEE Transactions on Automatic Control doi: 10.1109/TAC.2017.2713046 – volume: 17 start-page: 1 year: 2016 ident: 483_CR13 publication-title: The Journal of Machine Learning Research – volume: 17 start-page: 1117 issue: 6 year: 2019 ident: 483_CR26 publication-title: International Journal of Control, Automation and Systems doi: 10.1007/s12555-017-0717-7 – volume: 73 start-page: 572 year: 2018 ident: 483_CR18 publication-title: Applied Soft Computing doi: 10.1016/j.asoc.2018.08.044 – volume: 25 start-page: 944 issue: 2 year: 2015 ident: 483_CR2 publication-title: SIAM Journal on Optimization doi: 10.1137/14096668X – volume: 63 start-page: 6013 issue: 22 year: 2015 ident: 483_CR7 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2015.2461520 – volume: 31 start-page: 803 issue: 9 year: 1986 ident: 483_CR19 publication-title: IEEE Transactions on Automatic Control doi: 10.1109/TAC.1986.1104412 – ident: 483_CR12 – volume: 25 start-page: 2483 issue: 11 year: 2013 ident: 483_CR6 publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2012.191 – volume: 70 start-page: 3027 year: 2017 ident: 483_CR15 publication-title: Proceedings of the 34th International Conference on Machine Learning – volume: 7 start-page: 1421 issue: 3 year: 2020 ident: 483_CR25 publication-title: IEEE Transactions on Network Science and Engineering doi: 10.1109/TNSE.2019.2933177 – volume: 56 start-page: 350 issue: 1 year: 2008 ident: 483_CR3 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2007.906734 – volume: 58 start-page: 3816 issue: 7 year: 2010 ident: 483_CR20 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2010.2047721 – volume: 58 start-page: 5262 issue: 10 year: 2010 ident: 483_CR17 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2010.2055862 – volume: 65 start-page: 146 issue: 1 year: 2016 ident: 483_CR14 publication-title: IEEE Transactions on Signal Processing doi: 10.1109/TSP.2016.2617829
SSID	ssj0066297
Score	2.263988
Snippet	This paper investigates decentralized composite optimization problems involving a common non-smooth regularization term over an undirected and connected...
SourceID	nrf proquest crossref springer
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	3598
SubjectTerms	Algorithms Control Convergence Cost function Engineering Machine learning Mechatronics Optimization Performance degradation Regular Papers Regularization Robotics 제어계측공학
Title	An Edge-based Stochastic Proximal Gradient Algorithm for Decentralized Composite Optimization
URI	https://link.springer.com/article/10.1007/s12555-020-0483-9 https://www.proquest.com/docview/2589192953 https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002768067
Volume	19
WOSCitedRecordID	wos000692086100024&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
ispartofPNX	International Journal of Control, 2021, Automation, and Systems, 19(11), , pp.3598-3610
journalDatabaseRights	– providerCode: PRVAVX databaseName: Springer LINK customDbUrl: eissn: 2005-4092 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0066297 issn: 1598-6446 databaseCode: RSV dateStart: 20090201 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9tAEB7x6KEcgNIiwkurihPIkmM7Xu8x4n1JUUNRLmi1z2BBbOQYhPj1zDo2aVBBKidL9q5tzaxnPmtnvg9gTyqrWBQbTwoWeFHEEk9E1Pco023f-hYhuqrEJmivlwwG7KLu4x431e7NlmQVqafNboh-XTexK0dMQo_NwyJmu8TpNfzuXzXhN46DiaJKBx-LyT5utjL_dYuZZDSfFXYGZ77ZGq0yzsnKp951FZZrgEm6kxXxDeZMtgZLf9EOfofrbkaO9dBZbmw06Ze5uhGOr5lcFPlTOsLpp0VVClaS7t0wL9LyZkQQ3ZIjUxdzps840cUSV_NlyC8MPKO6o_MH_Dk5vjw882qZBU-FHb_0jDYiENpiNrNW6JDa0DKqqKVKVQRnDGGLkFqhS6VsCzxLldFSxDaKYx2E67CQ5ZnZAJL4kdVhZFwDb6RlIqSNRSB1KKluS6la4Df25qrmIHdSGHd8yp7sLMfRctxZjrMW7L9OuZ8QcHw0-Cc6kd-qlDvabHcc5vy24PhzcM6Zkx9M_BZsNz7m9Qc75oFTV0So2AlbcND4dHr53Sdu_tfoLfgauJqYqpdxGxbK4sHswBf1WKbjYrdaxy9d9O3c
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS9xAEB-qFdSH2vqBZ7Vdik-VQC7Zy2Yfj9Yvaq_iF76UZT_PoJdILi3Sv76zucSrUoX2KZDsZsPMZua3zMxvALaVdprTxAZK8iiglKeBpCwMGDfd0IUOIbqum02wwSC9vOTHTR33uM12b0OStaWeFrsh-vXVxD4dMY0DPgMvKTosT5h_cnrRmt8kiSYdVXq4LDr7pA1l_u0VD5zRTF66BzjzUWi09jh7S__1ra_hVQMwSX-yI97AC5svw-IftIMr8L2fk10z9JIbW0NOq0JfSc_XTI7L4i4b4fT9sk4Fq0j_ZliUWXU1IohuyWfbJHNmv3CityU-58uSb2h4Rk1F5yqc7-2efToImjYLgY57YRVYY2UkjUNv5pw0MXOx40wzx7SuCc44whapjEaVKtWVeJdpa5RMHE0SE8VrMJsXuV0HkobUmZhaX8BLjUqlcomMlIkVM12ldAfCVt5CNxzkvhXGjZiyJ3vJCZSc8JITvAMf76fcTgg4nhv8AZUornUmPG22vw4LcV0KPBwcCu7bD6ZhBzZbHYvmhx2LyHdXRKjYizuw0-p0-vjJFTf-afR7mD84-3okjg4HX97CQuTzY-q6xk2Yrcofdgvm9M8qG5fv6j39G4xO8MA
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwED6xghB74McYWmEMC_G0KWqauHH8WLGVTaBSaTDtBVn-2UVrkynNJsRfjy9NKJs2pImnSImdWHeO7yx_930AH5R2mtPEBkryKKCUp4GkLAwYN_3Qhc6n6LoWm2DjcXp6yieNzumiRbu3R5LLmgZkacqr3oVxvVXhm8-EsbIYoYlpHPA1eEgRR4_b9eOTdilOkmiprjLwQ_CBP2mPNW97xbXAtJaX7lrOeeOYtI4-o2f_Pe7n8LRJPMlwOVNewAObb8D6X3SEL-HHMCcHZooWXVhDjqtCn0nkcSaTsviZzX33T2UNEavIcDYtyqw6mxOf9ZJ924A8s1--I64xiAWz5KtfkOZNpecmfB8dfPt4GDTyC4GOB2EVWGNlJI3zUc45aWLmYseZZo5pXROfcZ_OSGW0d7VSfenvMm2NkomjSWKi-BV08iK3W0DSkDoTU4uFvdSoVCqXyEiZWDHTV0p3IWxtL3TDTY4SGTOxYlVGywlvOYGWE7wLu3-6XCyJOf7V-L13qDjXmUA6bbxOC3FeCr9pOBIcZQnTsAvbrb9F8yMvRISqiz6FHMRd2Gv9u3p85xdf36v1O3g82R-JL0fjz2_gSYSwmbrccRs6VXlp38IjfVVli3Knnt6_AXeR-aQ
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=An+Edge-based+Stochastic+Proximal+Gradient+Algorithm+for+Decentralized+Composite+Optimization&rft.jtitle=International+journal+of+control%2C+automation%2C+and+systems&rft.au=Zhang%2C+Ling&rft.au=Yan%2C+Yu&rft.au=Wang%2C+Zheng&rft.au=Li%2C+Huaqing&rft.date=2021-11-01&rft.issn=1598-6446&rft.eissn=2005-4092&rft.volume=19&rft.issue=11&rft.spage=3598&rft.epage=3610&rft_id=info:doi/10.1007%2Fs12555-020-0483-9&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s12555_020_0483_9
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1598-6446&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1598-6446&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1598-6446&client=summon