PMGT-VR: a Decentralized Proximal-gradient Algorithmic Framework with Variance Reduction
This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed fr...
Saved in:
| Published in: | IEEE transactions on pattern analysis and machine intelligence Vol. 48; no. 1; pp. 1 - 12 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
05.09.2025
|
| Subjects: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms. |
|---|---|
| AbstractList | This article considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms. This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms.This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms. This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms. |
| Author | Ye, Haishan Zhang, Tong Xiong, Wei |
| Author_xml | – sequence: 1 givenname: Haishan surname: Ye fullname: Ye, Haishan email: hsye_cs@outlook.com organization: Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China – sequence: 2 givenname: Wei surname: Xiong fullname: Xiong, Wei email: weixiong5237@gmail.com organization: The Hong Kong University of Science and Technology, China – sequence: 3 givenname: Tong surname: Zhang fullname: Zhang, Tong email: tongzhang@tongzhang-ml.org organization: The Hong Kong University of Science and Technology, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40911449$$D View this record in MEDLINE/PubMed |
| BookMark | eNpFkF1PwjAUhhuDkQ_9A8aYXXozbLuuW70jKEiCkRAk3i2lPcPqPrDbgvrrLYJ61eT0ed-c83RRqygLQOic4D4hWFwvZoOHSZ9iGvYDjnkcsSPUoYRjX1BBW6iDCad-HNO4jbpV9YoxYSEOTlCbYUEIY6KDnmcP44W_nN940rsFBUVtZWa-QHszW36YXGb-2kpt3Ic3yNalNfVLbpQ3sjKHbWnfvK2beEtpjSwUeHPQjapNWZyi41RmFZwd3h56Gt0thvf-9HE8GQ6mviKC1n4g0hRYCJKBSDHENKBMA0Aq41BHAJrjiMQiDeiKa8yBc6lDqohKA4gg5kEPXe17N7Z8b6Cqk9xUCrJMFlA2VeL6IhZx1-HQywParHLQyca6--xn8mvDAXQPKFtWlYX0DyE42SlPfpQnO-XJQbkLXexDxq39HyAkpKEQwTfafn0n |
| CODEN | ITPIDJ |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TPAMI.2025.3606874 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | 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 Electronic Library (IEL) 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 | Engineering Computer Science |
| EISSN | 2160-9292 1939-3539 |
| EndPage | 12 |
| ExternalDocumentID | 40911449 10_1109_TPAMI_2025_3606874 11152599 |
| Genre | orig-research Journal Article |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 5VS 9M8 AAYXX ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH CITATION FA8 H~9 IBMZZ ICLAB IFJZH RNI RZB VH1 NPM 7X8 |
| ID | FETCH-LOGICAL-c192t-39ffe45ea4e9f0e82324deeefa85d7eed607189f32b6d06e66ad52c1cf3e7e863 |
| IEDL.DBID | RIE |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Thu Oct 02 21:31:07 EDT 2025 Wed Dec 10 13:19:50 EST 2025 Sat Nov 29 07:23:24 EST 2025 Wed Oct 08 06:22:45 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| 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-c192t-39ffe45ea4e9f0e82324deeefa85d7eed607189f32b6d06e66ad52c1cf3e7e863 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 40911449 |
| PQID | 3247476189 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1109_TPAMI_2025_3606874 proquest_miscellaneous_3247476189 ieee_primary_11152599 pubmed_primary_40911449 |
| PublicationCentury | 2000 |
| PublicationDate | 20250905 |
| PublicationDateYYYYMMDD | 2025-09-05 |
| PublicationDate_xml | – month: 09 year: 2025 text: 20250905 day: 05 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0014503 |
| Score | 2.4887836 |
| Snippet | This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic... This article considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Complexity theory Convergence Decentralized optimization Loss measurement Network topology Optimization proximal-gradient Servers Symmetric matrices Topology Training variance reduction Vectors |
| Title | PMGT-VR: a Decentralized Proximal-gradient Algorithmic Framework with Variance Reduction |
| URI | https://ieeexplore.ieee.org/document/11152599 https://www.ncbi.nlm.nih.gov/pubmed/40911449 https://www.proquest.com/docview/3247476189 |
| Volume | 48 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB4B4rAceO_SfSAjcUOGtI6TeG_VsgUOoKrqVr1Fjj1hI0GDQooQv37HbsL20gO3HPJwPDOa7_O8AE7jrCcJDYU8VIHmYaIt18aGXJKrQJlpHWaZHzYR390l06kaNsXqvhYGEX3yGZ67Sx_Lt6WZu6OyC7JLSXBdrcN6HEeLYq33kEEo_RhkgjBk4sQj2gqZQF2Mh_3bG-KCPXkuCLAnsZvGQ8SGuIDrobnkkPyEldVg0zudwc4Hl7sL2w26ZP2FOuzBGs72Yaed3MAaQ96HraU2hAcwHd5ejflk9JNpdolNumbxhpYNq_K1eNQP_L7yqWE16z_cl1VR_30sDBu0iV3MneayCdFup0Ns5NrBOoEfwp_B7_Gva95MXOCGkF7NhcpzDCXqEFUeYOLglqX_ynUibUzu1HWjS1QuellkgwijSFvZM12TC4wxicRn2JiVMzwC1rWElTSxN1d_khniRbEQSnR1pI0UaDpw1m57-rRorJF6QhKo1MsrdfJKG3l14NDt7_87m63twEkrqpTswgU79AzL-XNKKyemFNFqO_BlIcP3p1vRf13x1m_wyX3cp5LJ77BRV3P8AZvmpS6eq2NSvmly7JXvHxG11Ak |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BQaIcWiilXT6NxA25zcZ2Eve2ApZWdFeraqn2Fjn2pERqN1WaRYhfz9iblF564JZDEk38PJr34vkA-JgWsSI2JLnUkeEyM44b6yRXFCpQFcbIogjDJtLpNFss9KwrVg-1MIgYks_wwF-Gs3xX25X_VXZIfqmIruuH8EhJGUfrcq3bQwOpwiBkIjHk5KQk-hqZSB_OZ6PJCanBWB0IouxZ6ufxkLQhNeC7aN4JSWHGyv10M4Sd8fZ_GvwMtjp-yUbrDfEcHuByB7b72Q2sc-UdeHqnEeELWMwm3-b8_OyIGfYFu4TN6g86Nmvq39WVueQXTUgOa9no8qJuqvbnVWXZuE_tYv5_Ljsn4e13ETvzDWE95LvwY_x1_vmYdzMXuCWu13KhyxKlQiNRlxFmnnA5-q7SZMqlFFB9P7pMlyIuEhclmCTGqdgObSkwxSwRL2FjWS9xH9jQEVsypN98BUphSRmlQmgxNImxSqAdwKd-2fPrdWuNPEiSSOcBr9zjlXd4DWDXr--_O7ulHcCHHqqcPMMfd5gl1qubnCwnrZSQtQPYW2N4-3QP_at73voenhzPJ6f56cn0-2vY9IaExDL1BjbaZoVv4bH91VY3zbuwBf8CQx3WaA |
| 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=PMGT-VR%3A+a+Decentralized+Proximal-gradient+Algorithmic+Framework+with+Variance+Reduction&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Ye%2C+Haishan&rft.au=Xiong%2C+Wei&rft.au=Zhang%2C+Tong&rft.date=2025-09-05&rft.issn=1939-3539&rft.eissn=1939-3539&rft.volume=PP&rft_id=info:doi/10.1109%2FTPAMI.2025.3606874&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |