Scalable Proximal Jacobian Iteration Method With Global Convergence Analysis for Nonconvex Unconstrained Composite Optimizations

The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the <inline-formula> <tex-math notation="LaTeX">l_{0} </tex-math></inline-formula>-norm and rank function minimization problems. However, due...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transaction on neural networks and learning systems Ročník 30; číslo 9; s. 2825 - 2839
Hlavní autori: Zhang, Hengmin, Qian, Jianjun, Gao, Junbin, Yang, Jian, Xu, Chunyan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.09.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:2162-237X, 2162-2388, 2162-2388
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the <inline-formula> <tex-math notation="LaTeX">l_{0} </tex-math></inline-formula>-norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov's acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyka-Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.
AbstractList The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the [Formula Omitted]-norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov’s acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyk–Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the l -norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov's acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyka-Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the l0 -norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov's acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyka-Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the l0 -norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov's acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyka-Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the <inline-formula> <tex-math notation="LaTeX">l_{0} </tex-math></inline-formula>-norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging. Inspired by the basic ideas of both the Jacobian alternating direction method of multipliers (JADMMs) for solving linearly constrained problems with separable objectives and the proximal gradient methods (PGMs) for optimizing the unconstrained problems with one variable, this paper focuses on extending the PGMs to the proximal Jacobian iteration methods (PJIMs) for handling with a family of nonconvex composite optimization problems with two splitting variables. To reduce the total computational complexity by decreasing the number of iterations, we devise the accelerated version of PJIMs through the well-known Nesterov's acceleration strategy and further extend both to solve the multivariable cases. Most importantly, we provide a rigorous convergence analysis, in theory, to show that the generated variable sequence globally converges to a critical point by exploiting the Kurdyka-Łojasiewica (KŁ) property for a broad class of functions. Furthermore, we also establish the linear and sublinear convergence rates of the obtained variable sequence in the objective function. As the specific application to the nonconvex sparse and low-rank recovery problems, several numerical experiments can verify that the newly proposed algorithms not only keep fast convergence speed but also have high precision.
Author Zhang, Hengmin
Xu, Chunyan
Qian, Jianjun
Yang, Jian
Gao, Junbin
Author_xml – sequence: 1
  givenname: Hengmin
  orcidid: 0000-0002-2472-6637
  surname: Zhang
  fullname: Zhang, Hengmin
  email: zhanghengmin@126.com
  organization: PCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing, China
– sequence: 2
  givenname: Jianjun
  orcidid: 0000-0002-0968-8556
  surname: Qian
  fullname: Qian, Jianjun
  email: csjqian@njust.edu.cn
  organization: PCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing, China
– sequence: 3
  givenname: Junbin
  orcidid: 0000-0001-9803-0256
  surname: Gao
  fullname: Gao, Junbin
  email: junbin.gao@sydney.edu.au
  organization: Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Sydney, NSW, Australia
– sequence: 4
  givenname: Jian
  orcidid: 0000-0003-4800-832X
  surname: Yang
  fullname: Yang, Jian
  email: csjyang@njust.edu.cn
  organization: Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
– sequence: 5
  givenname: Chunyan
  orcidid: 0000-0002-0814-4362
  surname: Xu
  fullname: Xu, Chunyan
  email: cyx@njust.edu.cn
  organization: Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30668503$$D View this record in MEDLINE/PubMed
BookMark eNp9kU1vEzEQhi1URD_oHwAJWeLSS4I_dr32sYqgFIUUqa3gtrK9s9TVxk5tB7Wc-Ol4k5BDD8xlRvLzzsjve4wOfPCA0BtKppQS9eFmsZhfTxmhcsqkrIVSL9ARo4JNGJfyYD83Pw7RaUr3pJQgtajUK3TIiRCyJvwI_bm2etBmAPwthke31AP-om0wTnt8mSHq7ILHXyHfhQ5_d_kOXwzBFGoW_C-IP8FbwOdeD0_JJdyHiBfB2_HtEd-OQ8pROw9dESxXIbkM-GqV3dL93qxOr9HLXg8JTnf9BN1--ngz-zyZX11czs7nE8trmifAVU1BsL4jvZS8MmDrvlGyA26sbGqtZG8lF1IxJig1XSMMGNNQK_peNMBP0Nl27yqGhzWk3C5dsjAM2kNYp5bRRlVUUFUV9P0z9D6sY_ljoVgjq-KkUoV6t6PWZgldu4rFvfjU_vO2AGwL2BhSitDvEUraMcN2k2E7ZtjuMiwi-UxkXd44Nfo4_F_6dit1ALC_JQXlhDf8LwDhq2Y
CODEN ITNNAL
CitedBy_id crossref_primary_10_1016_j_inffus_2024_102347
crossref_primary_10_1109_TCSVT_2023_3291821
crossref_primary_10_1109_TCYB_2020_3010960
crossref_primary_10_1109_TNNLS_2019_2900572
crossref_primary_10_1109_TNNLS_2023_3327716
crossref_primary_10_3390_s19143145
crossref_primary_10_1016_j_anucene_2024_110943
crossref_primary_10_1109_TNNLS_2022_3183970
crossref_primary_10_1016_j_image_2021_116569
crossref_primary_10_1109_TNNLS_2024_3395064
crossref_primary_10_23919_cje_2023_00_340
crossref_primary_10_1016_j_neucom_2024_128703
crossref_primary_10_1109_TIFS_2023_3337717
crossref_primary_10_1109_TMM_2022_3171088
crossref_primary_10_1007_s12652_020_02778_2
crossref_primary_10_1109_TIFS_2022_3172218
crossref_primary_10_1007_s11063_023_11424_9
crossref_primary_10_1016_j_neucom_2023_01_030
crossref_primary_10_1109_TGRS_2022_3172018
crossref_primary_10_1016_j_jfranklin_2023_01_041
Cites_doi 10.1109/TNNLS.2016.2573644
10.1109/ICCV.2013.309
10.1007/s00041-008-9045-x
10.1016/0024-3795(93)90211-6
10.1109/TPAMI.2015.2465956
10.1007/978-3-642-02431-3
10.1287/moor.1100.0449
10.1109/TIP.2017.2777183
10.1137/070697835
10.1007/s10107-013-0701-9
10.1007/s10107-014-0826-5
10.1109/TIP.2009.2028250
10.1109/TIP.2016.2599290
10.1137/050644641
10.1007/s10107-007-0133-5
10.24963/ijcai.2017/462
10.1109/TNNLS.2015.2436951
10.1198/016214501753382273
10.1007/s11263-016-0930-5
10.1109/TIP.2017.2745200
10.1109/TPAMI.2012.271
10.1214/09-AOS729
10.1016/j.patcog.2015.01.024
10.1109/TIP.2015.2481325
10.1109/TPAMI.2017.2748590
10.1137/15M1027528
10.1080/00401706.1993.10485033
10.1007/BF01581204
10.1137/080716542
10.1016/0898-1221(76)90003-1
10.1109/TNNLS.2016.2608834
10.1016/j.ins.2017.02.020
10.1109/TPAMI.2017.2651816
10.1007/s10107-011-0484-9
10.1109/TNNLS.2015.2500600
10.1109/TPAMI.2013.57
10.1109/JPROC.2009.2035722
10.1109/TIT.2013.2249572
10.1137/140990309
10.1109/TPAMI.2016.2535218
10.1109/ICCV.2013.34
10.1109/TIP.2004.836169
10.1561/2200000016
10.1109/TNNLS.2017.2690970
10.1109/TPAMI.2017.2689021
10.1109/TCYB.2018.2811764
10.1109/ICDM.2015.9
10.1088/0266-5611/24/3/035020
10.1109/ISIT.2010.5513535
10.1145/1970392.1970395
10.1007/s10115-013-0713-z
10.1016/j.jvcir.2012.10.006
10.1007/BF00927673
10.1137/1.9781611971309
10.1016/j.ins.2015.12.038
10.1137/080738970
10.1109/TIP.2015.2511584
10.5802/aif.1638
10.1109/TPAMI.2012.88
10.1109/TPAMI.2012.132
10.1109/TPAMI.2008.79
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
DOI 10.1109/TNNLS.2018.2885699
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Calcium & Calcified Tissue Abstracts
Ceramic Abstracts
Chemoreception Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Neurosciences Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Materials Research Database
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Materials Business File
Aerospace Database
Engineered Materials Abstracts
Biotechnology Research Abstracts
Chemoreception Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
Civil Engineering Abstracts
Aluminium Industry Abstracts
Electronics & Communications Abstracts
Ceramic Abstracts
Neurosciences Abstracts
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Solid State and Superconductivity Abstracts
Engineering Research Database
Calcium & Calcified Tissue Abstracts
Corrosion Abstracts
MEDLINE - Academic
DatabaseTitleList Materials Research Database
PubMed
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2162-2388
EndPage 2839
ExternalDocumentID 30668503
10_1109_TNNLS_2018_2885699
8613037
Genre orig-research
Journal Article
GrantInformation_xml – fundername: National Science Fund of China
  grantid: U1713208; 61472187; 61502235; 61876083; 61602244
– fundername: 973 Program
  grantid: 2014CB349303
– fundername: Program for Changjiang Scholars
– fundername: Fundamental Research Funds for the Central Universities
  grantid: 30918011321
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
MS~
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
NPM
RIG
7QF
7QO
7QP
7QQ
7QR
7SC
7SE
7SP
7SR
7TA
7TB
7TK
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
ID FETCH-LOGICAL-c351t-e3951e62fd0f8834bec5f798de3bc875a98fc8368922611bd76bebb71c6ff67e3
IEDL.DBID RIE
ISICitedReferencesCount 28
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000482589400021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2162-237X
2162-2388
IngestDate Sun Sep 28 00:49:44 EDT 2025
Sun Nov 09 06:23:15 EST 2025
Wed Feb 19 02:36:31 EST 2025
Sat Nov 29 01:40:02 EST 2025
Tue Nov 18 22:12:50 EST 2025
Wed Aug 27 02:41:42 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 9
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-c351t-e3951e62fd0f8834bec5f798de3bc875a98fc8368922611bd76bebb71c6ff67e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-9803-0256
0000-0002-2472-6637
0000-0003-4800-832X
0000-0002-0814-4362
0000-0002-0968-8556
PMID 30668503
PQID 2278400099
PQPubID 85436
PageCount 15
ParticipantIDs proquest_journals_2278400099
ieee_primary_8613037
crossref_primary_10_1109_TNNLS_2018_2885699
pubmed_primary_30668503
proquest_miscellaneous_2179416194
crossref_citationtrail_10_1109_TNNLS_2018_2885699
PublicationCentury 2000
PublicationDate 2019-09-01
PublicationDateYYYYMMDD 2019-09-01
PublicationDate_xml – month: 09
  year: 2019
  text: 2019-09-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev TNNLS
PublicationTitleAlternate IEEE Trans Neural Netw Learn Syst
PublicationYear 2019
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
ref56
ref12
ref59
ref15
ref58
ref14
ref52
ref11
gong (ref8) 2012
wang (ref38) 2015
ref54
wang (ref35) 2014
ref16
ref19
ref51
ref50
gong (ref47) 2013
ref46
ref45
ref48
ref42
ref41
ref44
nesterov (ref60) 1983; 27
ref43
ref49
lu (ref57) 2014
ref7
liu (ref18) 2013
ref4
ref3
ref6
zhang (ref2) 2010; 11
ref40
ref80
ref79
ref78
ref34
ref37
ref36
ref75
ref31
ref74
ref30
ref77
ref33
ref76
ref32
candès (ref27) 2009; 58
li (ref53) 2015
candés (ref5) 2008; 14
ref1
nesterov (ref70) 2013
nie (ref22) 2012
bolzano (ref71) 2012
lojasiewicz (ref39) 1963; 117
ref73
lin (ref17) 2010
ref72
toh (ref67) 2010; 6
ref68
ref24
ref23
ref69
ref25
ref64
ref20
ref63
ref66
zhang (ref10) 2016
ref65
ref21
ref28
ref29
lu (ref9) 2015
wright (ref26) 2009
zhong (ref55) 2014
ref62
ref61
References_xml – ident: ref7
  doi: 10.1109/TNNLS.2016.2573644
– year: 2015
  ident: ref38
  publication-title: Global convergence of ADMM in nonconvex nonsmooth optimization
– start-page: 2330
  year: 2016
  ident: ref10
  article-title: An alternating proximal splitting method with global convergence for nonconvex structured sparsity optimization
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– start-page: 655
  year: 2012
  ident: ref22
  article-title: Low-rank matrix recovery via efficient Schatten p-norm minimization
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– ident: ref76
  doi: 10.1109/ICCV.2013.309
– start-page: 2206
  year: 2014
  ident: ref55
  article-title: Gradient descent with proximal average for nonconvex and composite regularization
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– volume: 14
  start-page: 5
  year: 2008
  ident: ref5
  article-title: Enhancing sparsity by reweighted $\ell_{1}$ -minimization
  publication-title: J Fourier Anal Appl
  doi: 10.1007/s00041-008-9045-x
– ident: ref64
  doi: 10.1016/0024-3795(93)90211-6
– ident: ref51
  doi: 10.1109/TPAMI.2015.2465956
– ident: ref69
  doi: 10.1007/978-3-642-02431-3
– ident: ref42
  doi: 10.1287/moor.1100.0449
– ident: ref63
  doi: 10.1109/TIP.2017.2777183
– start-page: 37
  year: 2013
  ident: ref47
  article-title: A general iterative shrinkage and thresholding algorithm for non-convex regularized optimization problems
  publication-title: Proc Int Conf Mach Learn (ICML)
– ident: ref31
  doi: 10.1137/070697835
– ident: ref44
  doi: 10.1007/s10107-013-0701-9
– ident: ref58
  doi: 10.1007/s10107-014-0826-5
– ident: ref68
  doi: 10.1109/TIP.2009.2028250
– ident: ref65
  doi: 10.1109/TIP.2016.2599290
– ident: ref41
  doi: 10.1137/050644641
– ident: ref73
  doi: 10.1007/s10107-007-0133-5
– ident: ref54
  doi: 10.24963/ijcai.2017/462
– ident: ref33
  doi: 10.1109/TNNLS.2015.2436951
– volume: 27
  start-page: 372
  year: 1983
  ident: ref60
  article-title: A method of solving a convex programming problem with convergence rate $O(1/k^{2})$
  publication-title: Soviet Math Doklady
– ident: ref4
  doi: 10.1198/016214501753382273
– ident: ref50
  doi: 10.1007/s11263-016-0930-5
– start-page: 1988
  year: 2012
  ident: ref8
  article-title: Multi-stage multi-task feature learning
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– year: 2012
  ident: ref71
  publication-title: Theory of Science A Selection With an Introduction
– year: 2013
  ident: ref70
  publication-title: Introductory Lectures on Convex Optimization A Basic Course
– ident: ref56
  doi: 10.1109/TIP.2017.2745200
– ident: ref49
  doi: 10.1109/TPAMI.2012.271
– volume: 11
  start-page: 1081
  year: 2010
  ident: ref2
  article-title: Analysis of multi-stage convex relaxation for sparse regularization
  publication-title: J Mach Learn Res
– ident: ref3
  doi: 10.1214/09-AOS729
– year: 2014
  ident: ref35
  publication-title: Convergence of bregman alternating direction method with multipliers for nonconvex composite problems
– ident: ref11
  doi: 10.1016/j.patcog.2015.01.024
– volume: 6
  start-page: 615
  year: 2010
  ident: ref67
  article-title: An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems
  publication-title: Pacific J Optim
– ident: ref62
  doi: 10.1109/TIP.2015.2481325
– ident: ref77
  doi: 10.1109/TPAMI.2017.2748590
– ident: ref36
  doi: 10.1137/15M1027528
– ident: ref1
  doi: 10.1080/00401706.1993.10485033
– start-page: 379
  year: 2015
  ident: ref53
  article-title: Accelerated proximal gradient methods for nonconvex programming
  publication-title: Proc Adv Neural Inf Process Syst (NIPS)
– ident: ref59
  doi: 10.1007/BF01581204
– ident: ref66
  doi: 10.1137/080716542
– year: 2010
  ident: ref17
  publication-title: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices
– ident: ref15
  doi: 10.1016/0898-1221(76)90003-1
– ident: ref30
  doi: 10.1109/TNNLS.2016.2608834
– ident: ref52
  doi: 10.1016/j.ins.2017.02.020
– ident: ref78
  doi: 10.1109/TPAMI.2017.2651816
– ident: ref43
  doi: 10.1007/s10107-011-0484-9
– ident: ref29
  doi: 10.1109/TNNLS.2015.2500600
– ident: ref21
  doi: 10.1109/TPAMI.2013.57
– ident: ref24
  doi: 10.1109/JPROC.2009.2035722
– ident: ref25
  doi: 10.1109/TIT.2013.2249572
– start-page: 116
  year: 2013
  ident: ref18
  article-title: Linearized alternating direction method with parallel splitting and adaptive penalty for separable convex programs in machine learning
  publication-title: Proc Asian Conf Mach Learn
– ident: ref37
  doi: 10.1137/140990309
– ident: ref32
  doi: 10.1109/TPAMI.2016.2535218
– ident: ref6
  doi: 10.1109/ICCV.2013.34
– ident: ref79
  doi: 10.1109/TIP.2004.836169
– ident: ref16
  doi: 10.1561/2200000016
– ident: ref34
  doi: 10.1109/TNNLS.2017.2690970
– start-page: 1805
  year: 2015
  ident: ref9
  article-title: Generalized singular value thresholding
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– ident: ref19
  doi: 10.1109/TPAMI.2017.2689021
– ident: ref74
  doi: 10.1109/TCYB.2018.2811764
– volume: 117
  start-page: 87
  year: 1963
  ident: ref39
  article-title: Une propriété topologique des sous-ensembles analytiques réels
  publication-title: Les équations aux dérivées partielles
– start-page: 2080
  year: 2009
  ident: ref26
  article-title: Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization
  publication-title: Proc Adv Neural Inf Process Syst (NIPS)
– ident: ref46
  doi: 10.1109/ICDM.2015.9
– ident: ref48
  doi: 10.1088/0266-5611/24/3/035020
– ident: ref75
  doi: 10.1109/ISIT.2010.5513535
– volume: 58
  start-page: 1
  year: 2009
  ident: ref27
  article-title: Robust principal component analysis?
  publication-title: J ACM
  doi: 10.1145/1970392.1970395
– ident: ref12
  doi: 10.1007/s10115-013-0713-z
– ident: ref61
  doi: 10.1016/j.jvcir.2012.10.006
– start-page: 1251
  year: 2014
  ident: ref57
  article-title: Proximal iteratively reweighted algorithm with multiple splitting for nonconvex sparsity optimization
  publication-title: Proc Assoc Adv Artif Intell (AAAI)
– ident: ref14
  doi: 10.1007/BF00927673
– ident: ref72
  doi: 10.1137/1.9781611971309
– ident: ref13
  doi: 10.1016/j.ins.2015.12.038
– ident: ref23
  doi: 10.1137/080738970
– ident: ref45
  doi: 10.1109/TIP.2015.2511584
– ident: ref40
  doi: 10.5802/aif.1638
– ident: ref28
  doi: 10.1109/TPAMI.2012.88
– ident: ref80
  doi: 10.1109/TPAMI.2012.132
– ident: ref20
  doi: 10.1109/TPAMI.2008.79
SSID ssj0000605649
Score 2.4331214
Snippet The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the <inline-formula> <tex-math...
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the l -norm and rank function...
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the [Formula Omitted]-norm and...
The recent studies have found that the nonconvex relaxation functions usually perform better than the convex counterparts in the l0 -norm and rank function...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2825
SubjectTerms Acceleration
Algorithms
Basic converters
Computer applications
Convergence
Convexity
Critical point
Generalized proximal thresholding operators
global convergence analysis
Iterative methods
Jacobian matrices
kurdyka–Łojasiewica (KŁ) property
Learning systems
Linear programming
Minimization
nonconvex sparse and low-rank optimization
Nonlinear programming
Objective function
Optimization
proximal Jacobian iteration method (PJIM)
Title Scalable Proximal Jacobian Iteration Method With Global Convergence Analysis for Nonconvex Unconstrained Composite Optimizations
URI https://ieeexplore.ieee.org/document/8613037
https://www.ncbi.nlm.nih.gov/pubmed/30668503
https://www.proquest.com/docview/2278400099
https://www.proquest.com/docview/2179416194
Volume 30
WOSCitedRecordID wos000482589400021&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/IET Electronic Library (IEL) (UW System Shared)
  customDbUrl:
  eissn: 2162-2388
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000605649
  issn: 2162-237X
  databaseCode: RIE
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LbtUwEB21FQs2FCiPQKmMxA7SJnHixxJVVIAgVGor7i5KnIm4Ek3QfaAu--mdcZysAImdpdiOpTO2j-2ZOQBvnMZWN3UXY-FUnKeNjWvMVdzksrO21rXTrReb0GVpFgt7vgPv5lgYRPTOZ3jMRf-W3w5uy1dlJ4bJrtS7sKu1HmO15vuUhHi58mw3S1UWZ1IvphiZxJ5cluWXC3bkMseZMYWynC2U2LIyxSSXFbYkr7Hyd7rpt52z_f8b8EN4EOileD_awyPYwf4x7E_SDSLM5AO4vSBsOGpKnK-Gm-U1tflMayMnIBeffKJlwkt89fLS4vty80OM4gDilL3UfcAmiimhiSDiK8qh9x7sN-KKC2uvPYGt4H-zYxiKb7Q6XU9hn0_g6uzD5enHOIgxxE4W6SZGSVwMVda1SWeMzAn7otPWtCgbR4ee2prOGamMJUKXpk2rVYNNo1Onuk5plE9hrx96fA7CSVnTgT5j0ZucGIl1FqnHzhR0ttSJjSCd8KhcyFTOg_5Z-RNLYisPZ8VwVgHOCN7ObX6NeTr-WfuAwZprBpwiOJxgr8JUXlccK5x7Jh3B6_kzTUJ-Wal7HLZUh5e1lC-EIng2msvc92RlL_78z5dwn0YW3NYOYW-z2uIruOd-b5br1RFZ-sIceUu_A9Yk-gY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQXCpRHoICRuEHaJE78OKKKqoVtqNSt2FuUOBOxEk3QPlCP_HRmnMcJkLhZiu1Y-sb2Z3tmPoC3TmOtq7IJMXMqTOPKhiWmKqxS2Vhb6tLp2otN6Dw3i4W92IH3UywMInrnMzzkon_Lrzu35auyI8NkV-pbcDtL0yTuo7WmG5WImLnyfDeJVRImUi_GKJnIHs3zfHbJrlzmMDEmU5bzhRJfViYbBbOGTcmrrPydcPqN52Tv_4b8AO4PBFN86C3iIexg-wj2RvEGMczlffh1Sehw3JS4WHU3y2tq84lWR05BLs58qmVCTJx7gWnxdbn5Jnp5AHHMfuo-ZBPFmNJEEPUVedd6H_YbccWFtVefwFrwv9k1DMUXWp-ux8DPx3B18nF-fBoOcgyhk1m8CVESG0OVNHXUGCNTQj9rtDU1ysrRsae0pnFGKmOJ0sVxVWtVYVXp2KmmURrlE9htuxafgXBSlnSkT1j2JiVOYp1F6rExGZ0udWQDiEc8CjfkKudBfy_8mSWyhYezYDiLAc4A3k1tfvSZOv5Ze5_BmmoOOAVwMMJeDJN5XXC0cOq5dABvps80DfltpWyx21IdXthivhIK4GlvLlPfo5U9__M_X8Pd0_n5rJid5Z9fwD0a5eDEdgC7m9UWX8Id93OzXK9eeXv_DRQz_GU
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=Scalable+Proximal+Jacobian+Iteration+Method+With+Global+Convergence+Analysis+for+Nonconvex+Unconstrained+Composite+Optimizations&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Zhang%2C+Hengmin&rft.au=Qian%2C+Jianjun&rft.au=Gao%2C+Junbin&rft.au=Yang%2C+Jian&rft.date=2019-09-01&rft.eissn=2162-2388&rft.volume=30&rft.issue=9&rft.spage=2825&rft_id=info:doi/10.1109%2FTNNLS.2018.2885699&rft_id=info%3Apmid%2F30668503&rft.externalDocID=30668503
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon