An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems
Stochastic nonconvex minimax problems have attracted wide attention in machine learning, signal processing and many other fields in recent years. In this paper, we propose an accelerated first-order regularized momentum descent ascent algorithm (FORMDA) for solving stochastic nonconvex-concave minim...
Saved in:
| Published in: | Computational optimization and applications Vol. 90; no. 2; pp. 557 - 582 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
Springer Nature B.V
01.03.2025
|
| Subjects: | |
| ISSN: | 0926-6003, 1573-2894 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Stochastic nonconvex minimax problems have attracted wide attention in machine learning, signal processing and many other fields in recent years. In this paper, we propose an accelerated first-order regularized momentum descent ascent algorithm (FORMDA) for solving stochastic nonconvex-concave minimax problems. The iteration complexity of the algorithm is proved to be O~(ε-6.5) to obtain an ε-stationary point, which achieves the best-known complexity bound for single-loop algorithms to solve the stochastic nonconvex-concave minimax problems under the stationarity of the objective function. |
|---|---|
| AbstractList | Stochastic nonconvex minimax problems have attracted wide attention in machine learning, signal processing and many other fields in recent years. In this paper, we propose an accelerated first-order regularized momentum descent ascent algorithm (FORMDA) for solving stochastic nonconvex-concave minimax problems. The iteration complexity of the algorithm is proved to be O~(ε-6.5) to obtain an ε-stationary point, which achieves the best-known complexity bound for single-loop algorithms to solve the stochastic nonconvex-concave minimax problems under the stationarity of the objective function. |
| Author | Zhang, Huiling Xu, Zi |
| Author_xml | – sequence: 1 givenname: Huiling surname: Zhang fullname: Zhang, Huiling – sequence: 2 givenname: Zi orcidid: 0000-0003-0968-8027 surname: Xu fullname: Xu, Zi |
| BookMark | eNotkE9rAyEUxKWk0CTtF-hJ6NnWVXddjyH0HwR6ac_i6ttkw-6aqglpPn1tk9M8HsPM8JuhyehHQOi-oI8FpfIpFrSsFaFMEEorXhN1haZFKTlhtRITNKWKVaSilN-gWYxbSqmSnE3RaTFiYy30EEwCh9suxER8cBBwgPW-N6E75f_gBxjTfsAOos0XNhfp1z50aTPg1gcck7cbE1NncR5o_XiAI8lizQHw0I3dYI54F3zTwxBv0XVr-gh3F52jr5fnz-UbWX28vi8XK2IZqxIBKTijJSjRVLXiDmzNTSkb5UQluHKl407IRkgF1Ina2rYpRLY1oGRrpeNz9HDOzcXfe4hJb_0-jLlS80IyLlVZiuxiZ5cNPsYArd6FPDf86ILqP8b6zFhnxvqfsVb8F0y4dJc |
| Cites_doi | 10.1007/s10898-022-01169-5 10.23919/ACC55779.2023.10156371 10.1109/ICASSP.2015.7178500 10.1137/S1052623403425629 10.1057/palgrave.jors.2600425 10.1137/22M1482238 10.1007/978-3-319-41589-5_14 10.1007/s10107-019-01420-0 10.1137/18M1213488 10.1007/s10107-017-1161-4 10.1137/20M1313222 10.1007/s10107-006-0034-z 10.1137/20M1337600 10.1080/10556788.2021.1895152 10.1287/ijoo.2022.0004 10.1007/s10107-022-01919-z 10.1137/21M1465470 10.1007/s10107-015-0861-x 10.1007/s10589-020-00237-4 10.1109/TSP.2020.2986363 10.1137/23M1568168 10.1109/TSP.2010.2055862 10.1007/s10107-004-0552-5 10.1109/TSP.2011.2169407 10.1137/14095697X 10.1609/aaai.v33i01.33014739 10.1007/s10107-022-01910-8 |
| ContentType | Journal Article |
| Copyright | Copyright Springer Nature B.V. Mar 2025 |
| Copyright_xml | – notice: Copyright Springer Nature B.V. Mar 2025 |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1007/s10589-024-00638-9 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1573-2894 |
| EndPage | 582 |
| ExternalDocumentID | 10_1007_s10589_024_00638_9 |
| GroupedDBID | -Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 1N0 1SB 2.D 203 28- 29F 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 7WY 88I 8AO 8FE 8FG 8FL 8FW 8TC 8UJ 8VB 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAPKM AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYXX ABAKF ABBBX ABBRH ABBXA ABDBE ABDZT ABECU ABFSG ABFTV ABHLI ABHQN ABJCF ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACSTC ACZOJ ADHHG ADHIR ADHKG ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFEXP AFFHD AFGCZ AFHIU AFKRA AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGQPQ AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHQJS AHSBF AHWEU AHYZX AI. AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJBLW AJRNO AJZVZ AKVCP ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMVHM AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYJHY AZFZN AZQEC B-. BA0 BAPOH BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS CAG CCPQU CITATION COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EBLON EBS EBU EDO EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ7 GQ8 GROUPED_ABI_INFORM_RESEARCH GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K1G K60 K6V K6~ K7- KDC KOV KOW L6V LAK LLZTM M0C M2P M4Y M7S MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P62 P9R PF0 PHGZM PHGZT PQBIZ PQBZA PQGLB PQQKQ PROAC PT4 PT5 PTHSS Q2X QOK QOS QWB R4E R89 R9I RHV RNI RNS ROL RPX RSV RZC RZD RZK S16 S1Z S26 S27 S28 S3B SAP SCLPG SDD SDH SDM SHX SISQX SJYHP SMT SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TEORI TH9 TN5 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW VH1 W23 W48 WK8 YLTOR Z45 ZL0 ZMTXR ZWQNP ~8M ~EX 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c226t-e743205e94b6893dec83a57b9d46439d5d3d47b479e0d48ccfb143debe97fc7d3 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001386528600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0926-6003 |
| IngestDate | Wed Nov 26 14:52:55 EST 2025 Sat Nov 29 08:15:12 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c226t-e743205e94b6893dec83a57b9d46439d5d3d47b479e0d48ccfb143debe97fc7d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-0968-8027 |
| PQID | 3172379554 |
| PQPubID | 30811 |
| PageCount | 26 |
| ParticipantIDs | proquest_journals_3172379554 crossref_primary_10_1007_s10589_024_00638_9 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-03-00 20250301 |
| PublicationDateYYYYMMDD | 2025-03-01 |
| PublicationDate_xml | – month: 03 year: 2025 text: 2025-03-00 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | Computational optimization and applications |
| PublicationYear | 2025 |
| Publisher | Springer Nature B.V |
| Publisher_xml | – name: Springer Nature B.V |
| References | J Zhang (638_CR56) 2020; 33 T Tieleman (638_CR48) 2012; 4 S Lee (638_CR30) 2021; 34 V Tominin (638_CR47) 2023; 15 L Luo (638_CR26) 2020; 33 638_CR46 D Ostrovskii (638_CR39) 2021; 31 638_CR43 638_CR41 W Pan (638_CR40) 2021; 78 A Nemirovski (638_CR34) 2004; 15 638_CR49 638_CR2 638_CR1 638_CR51 J Yang (638_CR54) 2020; 33 RI Bot (638_CR5) 2023; 33 638_CR13 G Lan (638_CR22) 2016; 155 Y Nesterov (638_CR35) 2005; 103 H Rafique (638_CR42) 2022; 37 638_CR57 638_CR11 638_CR55 Y Chen (638_CR7) 2017; 165 638_CR10 Y Ouyang (638_CR38) 2021; 185 Z Xu (638_CR52) 2024; 34 638_CR19 638_CR18 638_CR16 Z Xu (638_CR53) 2023; 24 X Zhang (638_CR58) 2022; 35 H Lin (638_CR24) 2018; 18 638_CR25 638_CR23 S Lu (638_CR29) 2020; 68 638_CR21 C Song (638_CR44) 2020; 33 638_CR4 638_CR6 638_CR8 Z Xu (638_CR50) 2023; 201 B Grimmer (638_CR12) 2023; 201 638_CR28 638_CR9 638_CR27 W Kong (638_CR20) 2021; 31 R Giordano (638_CR14) 2018; 19 J Shen (638_CR45) 2022 G Mateos (638_CR32) 2010; 58 DP Bertsekas (638_CR3) 1997; 48 Y Ouyang (638_CR37) 2015; 8 EY Hamedani (638_CR17) 2021; 31 638_CR33 F Huang (638_CR15) 2022; 23 638_CR31 Y Nesterov (638_CR36) 2007; 109 |
| References_xml | – year: 2022 ident: 638_CR45 publication-title: J. Glob. Optim. doi: 10.1007/s10898-022-01169-5 – ident: 638_CR49 – ident: 638_CR1 – ident: 638_CR4 doi: 10.23919/ACC55779.2023.10156371 – ident: 638_CR25 doi: 10.1109/ICASSP.2015.7178500 – volume: 15 start-page: 433 issue: 2 year: 2023 ident: 638_CR47 publication-title: Computer – volume: 15 start-page: 229 issue: 1 year: 2004 ident: 638_CR34 publication-title: SIAM J. Optim. doi: 10.1137/S1052623403425629 – ident: 638_CR16 – ident: 638_CR31 – volume: 48 start-page: 334 issue: 3 year: 1997 ident: 638_CR3 publication-title: J. Oper. Res. Soc. doi: 10.1057/palgrave.jors.2600425 – ident: 638_CR19 doi: 10.1137/22M1482238 – ident: 638_CR23 – ident: 638_CR13 doi: 10.1007/978-3-319-41589-5_14 – volume: 34 start-page: 22588 year: 2021 ident: 638_CR30 publication-title: Adv. Neural. Inf. Process. Syst. – volume: 185 start-page: 1 issue: 1 year: 2021 ident: 638_CR38 publication-title: Math. Progr. doi: 10.1007/s10107-019-01420-0 – volume: 31 start-page: 1299 issue: 2 year: 2021 ident: 638_CR17 publication-title: SIAM J. Optim. doi: 10.1137/18M1213488 – volume: 165 start-page: 113 issue: 1 year: 2017 ident: 638_CR7 publication-title: Math. Progr. doi: 10.1007/s10107-017-1161-4 – volume: 31 start-page: 2558 issue: 4 year: 2021 ident: 638_CR20 publication-title: SIAM J. Optim. doi: 10.1137/20M1313222 – volume: 18 start-page: 1 issue: 212 year: 2018 ident: 638_CR24 publication-title: J. Mach. Learn. Res. – ident: 638_CR27 – ident: 638_CR2 – volume: 19 start-page: 1 issue: 51 year: 2018 ident: 638_CR14 publication-title: J. Mach. Learn. Res. – volume: 109 start-page: 319 issue: 2 year: 2007 ident: 638_CR36 publication-title: Math. Progr. doi: 10.1007/s10107-006-0034-z – volume: 31 start-page: 2508 issue: 4 year: 2021 ident: 638_CR39 publication-title: SIAM J. Optim. doi: 10.1137/20M1337600 – volume: 37 start-page: 1087 issue: 3 year: 2022 ident: 638_CR42 publication-title: Optim. Methods Softw. doi: 10.1080/10556788.2021.1895152 – ident: 638_CR6 – ident: 638_CR51 – volume: 24 start-page: 1 issue: 313 year: 2023 ident: 638_CR53 publication-title: J. Mach. Learn. Res. – volume: 35 start-page: 21668 year: 2022 ident: 638_CR58 publication-title: Adv. Neural. Inf. Process. Syst. – ident: 638_CR18 doi: 10.1287/ijoo.2022.0004 – ident: 638_CR55 – volume: 201 start-page: 635 year: 2023 ident: 638_CR50 publication-title: Math. Progr. doi: 10.1007/s10107-022-01919-z – ident: 638_CR43 – ident: 638_CR28 – volume: 33 start-page: 1884 issue: 3 year: 2023 ident: 638_CR5 publication-title: SIAM J. Optim. doi: 10.1137/21M1465470 – volume: 155 start-page: 511 issue: 1–2 year: 2016 ident: 638_CR22 publication-title: Math. Progr. doi: 10.1007/s10107-015-0861-x – volume: 78 start-page: 287 issue: 1 year: 2021 ident: 638_CR40 publication-title: Comput. Optim. Appl. doi: 10.1007/s10589-020-00237-4 – ident: 638_CR10 – ident: 638_CR33 – volume: 33 start-page: 20566 year: 2020 ident: 638_CR26 publication-title: NeurIPS – volume: 33 start-page: 14303 year: 2020 ident: 638_CR44 publication-title: Adv. Neural. Inf. Process. Syst. – volume: 33 start-page: 1153 year: 2020 ident: 638_CR54 publication-title: Adv. Neural Inf. Process. Syst. – volume: 68 start-page: 3676 year: 2020 ident: 638_CR29 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.2986363 – volume: 34 start-page: 1879 issue: 2 year: 2024 ident: 638_CR52 publication-title: SIAM J. Optim. doi: 10.1137/23M1568168 – ident: 638_CR21 – ident: 638_CR46 – volume: 4 start-page: 26 issue: 2 year: 2012 ident: 638_CR48 publication-title: COURSERA Neural Netw. Mach. Learn. – volume: 58 start-page: 5262 issue: 10 year: 2010 ident: 638_CR32 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2010.2055862 – volume: 103 start-page: 127 year: 2005 ident: 638_CR35 publication-title: Math. Progr. doi: 10.1007/s10107-004-0552-5 – ident: 638_CR11 – volume: 23 start-page: 1 year: 2022 ident: 638_CR15 publication-title: J. Mach. Learn. Res. – ident: 638_CR9 doi: 10.1109/TSP.2011.2169407 – ident: 638_CR8 – volume: 8 start-page: 644 issue: 1 year: 2015 ident: 638_CR37 publication-title: SIAM J. Imaging Sci. doi: 10.1137/14095697X – ident: 638_CR41 doi: 10.1609/aaai.v33i01.33014739 – ident: 638_CR57 – volume: 33 start-page: 7377 year: 2020 ident: 638_CR56 publication-title: Adv. Neural. Inf. Process. Syst. – volume: 201 start-page: 373 issue: 1–2 year: 2023 ident: 638_CR12 publication-title: Math. Progr. doi: 10.1007/s10107-022-01910-8 |
| SSID | ssj0009732 |
| Score | 2.398695 |
| Snippet | Stochastic nonconvex minimax problems have attracted wide attention in machine learning, signal processing and many other fields in recent years. In this... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Index Database |
| StartPage | 557 |
| SubjectTerms | Algorithms Complexity Machine learning Methods Minimax technique Momentum Optimization Random variables Signal processing |
| Title | An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems |
| URI | https://www.proquest.com/docview/3172379554 |
| Volume | 90 |
| WOSCitedRecordID | wos001386528600001&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: PRVAVX databaseName: Springer Nature Consortium list (Orbis Cascade Alliance) customDbUrl: eissn: 1573-2894 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009732 issn: 0926-6003 databaseCode: RSV dateStart: 19970101 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/eLvHCXMwlZ3PS8MwFMfDGB704G9xOiUHbxro0rRpjkMcHmSIv9it5FddwW7SdWPsr_cl65gDPewU6CEt77V9n5C87xehG6psSIOMk5jxCBYomXA2L4Ykyu0acqZC5TP9xPv9ZDAQzw109-8Ovmtyi9yxHsqIr6_Edet1YursCl5eP9YKu9y7kQWCxgSqeFh3yPw9xWYV2vwJ-8rSO9jumQ7Rfk2QuLtM-RFq2NEx2vulK3iCFt0RllpDRXFCEAZnOTAe8SqbuPTm82W-gOuFk1-opgU2S1EnLOvh63Nc5tWwwIC0GPBQD6XTc8aj8cgfU58TGLScWeykSQo5x7UxzeQUvfce3u4fSW2yQDSQV0UsIAQNIiuYioFdjNVJKCOuhGEOVkxkQsO4YlzYwLBE60wBYhnIveCZ5iY8Q024uT1HmFsuOlpmNJGGGQZ5hrWUUUmgIqeBSFvodhX09HuppZGuVZNdRFOIaOojmooWaq_yktbf1SQF2qEhF8BAF1tNdol2qTPu9YfH2qhZlVN7hXb0rMon5bV_kX4AMEXCCQ |
| linkProvider | Springer Nature |
| 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+accelerated+first-order+regularized+momentum+descent+ascent+algorithm+for+stochastic+nonconvex-concave+minimax+problems&rft.jtitle=Computational+optimization+and+applications&rft.au=Zhang%2C+Huiling&rft.au=Xu%2C+Zi&rft.date=2025-03-01&rft.issn=0926-6003&rft.eissn=1573-2894&rft.volume=90&rft.issue=2&rft.spage=557&rft.epage=582&rft_id=info:doi/10.1007%2Fs10589-024-00638-9&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s10589_024_00638_9 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0926-6003&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0926-6003&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0926-6003&client=summon |