Single-Loop Variance-Reduced Stochastic Algorithm for Nonconvex-Concave Minimax Optimization

Nonconvex-concave (NC-C) finite-sum minimax problems have broad applications in decentralized optimization and various machine learning tasks. However, the nonsmooth nature of NC-C problems makes it challenging to design effective variance reduction techniques. Existing vanilla stochastic algorithms...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 1 - 5
Hlavní autori: Jiang, Xia, Zhu, Linglingzhi, Zheng, Taoli, So, Anthony Man-Cho
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 06.04.2025
Predmet:
ISSN:2379-190X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Nonconvex-concave (NC-C) finite-sum minimax problems have broad applications in decentralized optimization and various machine learning tasks. However, the nonsmooth nature of NC-C problems makes it challenging to design effective variance reduction techniques. Existing vanilla stochastic algorithms using uniform samples for gradient estimation often exhibit slow convergence rates and require bounded variance assumptions. In this paper, we develop a novel probabilistic variance reduction updating scheme and propose a single-loop algorithm called the probabilistic variance-reduced smoothed gradient descent-ascent (PVR-SGDA) algorithm. The proposed algorithm achieves an iteration complexity of {\mathcal{O}}\left({{\varepsilon ^{ - 4}}}\right), surpassing the best-known rates of stochastic algorithms for NC-C minimax problems and matching the performance of the best deterministic algorithms in this context. Finally, we demonstrate the effectiveness of the proposed algorithm through numerical simulations.
AbstractList Nonconvex-concave (NC-C) finite-sum minimax problems have broad applications in decentralized optimization and various machine learning tasks. However, the nonsmooth nature of NC-C problems makes it challenging to design effective variance reduction techniques. Existing vanilla stochastic algorithms using uniform samples for gradient estimation often exhibit slow convergence rates and require bounded variance assumptions. In this paper, we develop a novel probabilistic variance reduction updating scheme and propose a single-loop algorithm called the probabilistic variance-reduced smoothed gradient descent-ascent (PVR-SGDA) algorithm. The proposed algorithm achieves an iteration complexity of {\mathcal{O}}\left({{\varepsilon ^{ - 4}}}\right), surpassing the best-known rates of stochastic algorithms for NC-C minimax problems and matching the performance of the best deterministic algorithms in this context. Finally, we demonstrate the effectiveness of the proposed algorithm through numerical simulations.
Author So, Anthony Man-Cho
Zheng, Taoli
Jiang, Xia
Zhu, Linglingzhi
Author_xml – sequence: 1
  givenname: Xia
  surname: Jiang
  fullname: Jiang, Xia
  email: xiajiang@cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management
– sequence: 2
  givenname: Linglingzhi
  surname: Zhu
  fullname: Zhu, Linglingzhi
  email: llzzhu@se.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management
– sequence: 3
  givenname: Taoli
  surname: Zheng
  fullname: Zheng, Taoli
  email: tlzheng@se.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management
– sequence: 4
  givenname: Anthony Man-Cho
  surname: So
  fullname: So, Anthony Man-Cho
  email: manchoso@se.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management
BookMark eNo1UFFLwzAYjKLgNvcPfIg_IPNL0zTJ4xg6henEDvFBGGn2dYu0yWjrmP56C-rL3XEHx3FDchZiQEKuOUw4B3PzMJvm-XNqsgwmCSRywkFrAzo7IWOjjBYSRKZVyk_JIBHKMG7g7YIM2_YDAPpAD8h77sO2QraIcU9fbeNtcMhecPPpcEPzLrqdbTvv6LTaxsZ3u5qWsaFPMbgYDnhks17ZA9JHH3xtj3S573ztv23nY7gk56WtWhz_8Yis7m5Xs3u2WM778QvmjehYKrkqDS-EScFIm1gtiwKFKDn26CRaUCALY0BKLnoTlILCuQydcoUGMSJXv7UeEdf7pt_RfK3_zxA_htFX0w
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP49660.2025.10889086
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350368741
EISSN 2379-190X
EndPage 5
ExternalDocumentID 10889086
Genre orig-research
GroupedDBID 23M
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i93t-4517f91b394095a2a85bbe33f1ee33c5ea0705b99055131ee0770bcc6ec7cb803
IEDL.DBID RIE
IngestDate Wed Nov 19 08:27:13 EST 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-4517f91b394095a2a85bbe33f1ee33c5ea0705b99055131ee0770bcc6ec7cb803
PageCount 5
ParticipantIDs ieee_primary_10889086
PublicationCentury 2000
PublicationDate 2025-April-6
PublicationDateYYYYMMDD 2025-04-06
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-6
  day: 06
PublicationDecade 2020
PublicationTitle Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998)
PublicationTitleAbbrev ICASSP
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.2946823
Snippet Nonconvex-concave (NC-C) finite-sum minimax problems have broad applications in decentralized optimization and various machine learning tasks. However, the...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Complexity theory
Convergence
Machine learning algorithms
nonconvex-concave minimax optimization
Numerical simulation
Optimization
Probabilistic logic
Signal processing
Signal processing algorithms
single-loop
Smoothing methods
Speech processing
stochastic algorithm
variance reduction
Title Single-Loop Variance-Reduced Stochastic Algorithm for Nonconvex-Concave Minimax Optimization
URI https://ieeexplore.ieee.org/document/10889086
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFA5uiOiLt4l3Ivia2UvSpI9jOBR0DjtkD8JIstQVtnbMbuzne5Jd1AcffGlLoA2cw8l30pzzfQjdxjQ0mlFOeOqHhPrUJ5CFKALY6OlAACZ60olN8HZb9HpxZ9Ws7nphjDGu-MzU7aM7yx8UemZ_lUGEC_iEiCqowjlfNmttll3BqdhBNysSzbvHZiNJOtSST8IuMGD19cu_ZFQcirT2_zn_Aap99-PhzgZpDtGWyY_Q3g8qwWP0nsBtZMhTUUzwG2yArTfJqyVmNQOclIUeSkvJjBujj2KalcMxhnQVt4vc1Z0vCEyl5dzg5yzPxnKBX2AtGa-aNGuo27rvNh_ISjmBZHFYEsp8noLFrep5zGQgBVPKhGHqG7hqZiQEOlMARFbeBQY9zj2ldWQ010p44Qmq5kVuThGWIpIRpBE8pIzqiMrAVzaIFQt1mgbmDNWsnfqTJTdGf22i8z_GL9Cu9YarfYkuUbWczswV2tbzMvucXjuPfgFLFKGL
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT8IwFG4UjZcXbxjv1sTX4i7t2j0SIpEIkwgxPJiQrnSyBDaCg_DzPR0D9cEHX7alyS45J6ffaXfO9yF071NXK0Y54ZHtEmpTm0AWEhLARks5AjDRkrnYBA8C0ev57aJZPe-F0VrnxWe6Yi7zf_mDVM3MVhlEuIBHCG8TbTFKHXvZrrWeeAWnYgfdFTSaD41atdNpU0M_CetAh1VWt_8SUslxpH7wzy84ROXvjjzcXmPNEdrQyTHa_0EmeILeO3AaadJM0wl-gyWw8Sd5NdSseoA7WaqG0pAy4-roI53G2XCMIWHFQZrklecLAq9Scq5xK07isVzgF5hNxkWbZhl164_d2hMptBNI7LsZoczmEdjc6J77TDpSsDDUrhvZGo6KaQmhzkKAIiPwAoMW51aolKcVV6Gw3FNUStJEnyEshSc9SCS4SxlVHpWOHZowDpmrosjR56hs7NSfLNkx-isTXfwxfot2n7qtZr_ZCJ4v0Z7xTF4J412hUjad6Wu0reZZ_Dm9yb37Bd-apNI
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Single-Loop+Variance-Reduced+Stochastic+Algorithm+for+Nonconvex-Concave+Minimax+Optimization&rft.au=Jiang%2C+Xia&rft.au=Zhu%2C+Linglingzhi&rft.au=Zheng%2C+Taoli&rft.au=So%2C+Anthony+Man-Cho&rft.date=2025-04-06&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FICASSP49660.2025.10889086&rft.externalDocID=10889086