Inertial accelerated stochastic mirror descent for large-scale generalized tensor CP decomposition
The majority of classic tensor CP decomposition models are designed for squared loss, utilizing Euclidean distance as a local proximal term. However, the Euclidean distance is unsuitable for the generalized loss function applicable to diverse types of real-world data, such as integer and binary data...
Saved in:
| Published in: | Computational optimization and applications Vol. 91; no. 1; pp. 201 - 233 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
Springer Nature B.V
01.05.2025
|
| Subjects: | |
| ISSN: | 0926-6003, 1573-2894 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The majority of classic tensor CP decomposition models are designed for squared loss, utilizing Euclidean distance as a local proximal term. However, the Euclidean distance is unsuitable for the generalized loss function applicable to diverse types of real-world data, such as integer and binary data. Consequently, algorithms developed under the squared loss are not easily adaptable to handle these generalized losses, partially due to the absence of the gradient Lipschitz continuity. This paper explores generalized tensor CP decomposition, employing the Bregman distance as the proximal term and introducing an inertial accelerated block randomized stochastic mirror descent algorithm (iTableSMD). Within a broader multi-block variance reduction and inertial acceleration framework, we demonstrate the sublinear convergence rate for the subsequential sequence produced by the iTableSMD algorithm. We further show that iTableSMD requires at most O(ε-2) iterations in expectation to attain an ε-stationary point and establish the global convergence of the sequence. Numerical experiments on real datasets demonstrate that our proposed algorithm is efficient and achieves better performance than the existing state-of-the-art methods. |
|---|---|
| AbstractList | The majority of classic tensor CP decomposition models are designed for squared loss, utilizing Euclidean distance as a local proximal term. However, the Euclidean distance is unsuitable for the generalized loss function applicable to diverse types of real-world data, such as integer and binary data. Consequently, algorithms developed under the squared loss are not easily adaptable to handle these generalized losses, partially due to the absence of the gradient Lipschitz continuity. This paper explores generalized tensor CP decomposition, employing the Bregman distance as the proximal term and introducing an inertial accelerated block randomized stochastic mirror descent algorithm (iTableSMD). Within a broader multi-block variance reduction and inertial acceleration framework, we demonstrate the sublinear convergence rate for the subsequential sequence produced by the iTableSMD algorithm. We further show that iTableSMD requires at most O(ε-2) iterations in expectation to attain an ε-stationary point and establish the global convergence of the sequence. Numerical experiments on real datasets demonstrate that our proposed algorithm is efficient and achieves better performance than the existing state-of-the-art methods. |
| Author | Cui, Chunfeng Wang, Qingsong Xia, Yong Liu, Zehui |
| Author_xml | – sequence: 1 givenname: Zehui surname: Liu fullname: Liu, Zehui – sequence: 2 givenname: Qingsong surname: Wang fullname: Wang, Qingsong – sequence: 3 givenname: Chunfeng orcidid: 0000-0002-6815-4060 surname: Cui fullname: Cui, Chunfeng – sequence: 4 givenname: Yong surname: Xia fullname: Xia, Yong |
| BookMark | eNotkE1LAzEQhoNUsK3-AU8LnqOTZD-yRylqCwU96DnkY7ambDc1SaH6691aT_PCPO8MPDMyGcKAhNwyuGcAzUNiUMmWAq8oQF1LerwgU1Y1gnLZlhMyhZbXtAYQV2SW0hYA2kbwKTGrAWP2ui-0tdhj1BldkXKwnzplb4udjzHEwmGyOOSiG3Ov4wZpsrrHYoNjX_f-Z2xlHNK4XryNtA27fUg--zBck8tO9wlv_uecfDw_vS-WdP36slo8rqnlvM7UoeQNdMJZjqZmxpamdVULQjhTApfcMeu6incaXVVWJYCVpimFka11GkHMyd357j6GrwOmrLbhEIfxpRJMQlMzYCeKnykbQ0oRO7WPfqfjt2KgTi7V2aUaXao_l-oofgEIEGtt |
| Cites_doi | 10.1016/j.cam.2022.114948 10.1016/S0167-6377(02)00231-6 10.1137/07070111X 10.1137/19M1266265 10.1137/070704277 10.1137/20M1387213 10.1002/1099-128X(200005/06)14:3<285::AID-CEM584>3.0.CO;2-1 10.1037/h0054245 10.1007/s10618-013-0341-y 10.1007/BF02288739 10.1137/100808034 10.1287/ijoo.2018.0008 10.1007/s43670-022-00021-x 10.1109/TSP.2020.2982321 10.1109/TSP.2022.3163896 10.1002/sapm19287139 10.1137/18M1203626 10.1137/17M1138558 10.1007/s11336-008-9056-1 10.1137/17M1112303 10.1007/s40305-021-00368-3 10.1109/TSP.2013.2269903 10.1016/j.apnum.2023.03.014 10.1109/TSP.2020.2975353 10.1002/sapm192761164 10.1137/19M1298007 10.1609/aaai.v38i14.29485 10.1109/TSP.2016.2576427 10.1137/19M1271750 10.1137/130936361 10.1109/LSP.2019.2938663 10.1007/s10107-013-0701-9 10.1016/0041-5553(64)90137-5 10.1137/16M1099546 10.1007/978-3-030-39568-1 10.1080/10556788.2023.2189717 10.1137/18M1178244 10.1587/transfun.E92.A.708 10.1007/BF02310791 10.1109/TSP.2020.3010719 10.1109/TKDE.2019.2962031 10.1137/16M1064064 10.1002/cem.1236 10.1002/cem.1244 10.1137/120868323 10.1109/ACSSC.2017.8335432 10.1023/A:1017501703105 10.1137/120887795 10.1137/110859063 10.1287/moor.2016.0817 10.1137/21M140376X |
| ContentType | Journal Article |
| Copyright | Copyright Springer Nature B.V. May 2025 |
| Copyright_xml | – notice: Copyright Springer Nature B.V. May 2025 |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1007/s10589-025-00668-x |
| 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 | 233 |
| ExternalDocumentID | 10_1007_s10589_025_00668_x |
| 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-de8270f3dc2eb61bc4b9d59033db40282d1cdf52faed545400c8b743b89cdae03 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001423026400001&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 14:41:30 EST 2025 Sat Nov 29 08:04:04 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c226t-de8270f3dc2eb61bc4b9d59033db40282d1cdf52faed545400c8b743b89cdae03 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-6815-4060 |
| PQID | 3180761010 |
| PQPubID | 30811 |
| PageCount | 33 |
| ParticipantIDs | proquest_journals_3180761010 crossref_primary_10_1007_s10589_025_00668_x |
| PublicationCentury | 2000 |
| PublicationDate | 2025-05-00 20250501 |
| PublicationDateYYYYMMDD | 2025-05-01 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-05-00 |
| 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 | 668_CR36 668_CR38 L-H Lim (668_CR4) 2009; 23 668_CR37 Q Wang (668_CR43) 2021; 17 BT Polyak (668_CR45) 1964; 4 L Sorber (668_CR14) 2013; 23 P Latafat (668_CR57) 2022; 32 A Defazio (668_CR58) 2014; 27 JD Carroll (668_CR6) 1970; 35 D Hong (668_CR16) 2020; 62 G Lan (668_CR55) 2020 B Ermiş (668_CR24) 2015; 29 X Fu (668_CR48) 2020; 68 TG Kolda (668_CR32) 2009; 51 T Pock (668_CR10) 2016; 9 YE Nesterov (668_CR60) 1983; 27 J Bolte (668_CR9) 2014; 146 Y Xu (668_CR7) 2013; 6 A-H Phan (668_CR12) 2013; 61 FL Hitchcock (668_CR27) 1927; 6 J Bolte (668_CR35) 2018; 28 H Lu (668_CR39) 2019; 1 668_CR5 668_CR61 668_CR3 668_CR63 668_CR62 668_CR21 668_CR20 M Vandecappelle (668_CR19) 2020; 68 M Teboulle (668_CR26) 2020; 13 Q Wang (668_CR64) 2023; 189 P Comon (668_CR13) 2009; 23 A Yeredor (668_CR51) 2019; 26 J Hertrich (668_CR50) 2022; 20 WP Krijnen (668_CR1) 2008; 73 Q Wang (668_CR44) 2023; 423 P Paatero (668_CR2) 2000; 14 EC Chi (668_CR25) 2012; 33 668_CR59 Q Wang (668_CR46) 2023; 38 H Lu (668_CR54) 2018; 28 K Huang (668_CR11) 2016; 64 A Beck (668_CR42) 2003; 31 W Pu (668_CR40) 2022; 70 D Han (668_CR8) 2022; 10 HH Bauschke (668_CR52) 2017; 42 A Nemirovski (668_CR56) 2009; 19 FL Hitchcock (668_CR28) 1928; 7 D Driggs (668_CR49) 2021; 14 TG Kolda (668_CR17) 2019; 2 C Battaglino (668_CR34) 2018; 39 RB Cattell (668_CR30) 1952; 49 A Cichocki (668_CR33) 2009; 92 668_CR47 A-H Phan (668_CR15) 2013; 34 CD Dang (668_CR41) 2015; 25 R Cattell (668_CR29) 1944; 9 M Wang (668_CR18) 2020; 21 L Cheng (668_CR23) 2020; 68 X Fu (668_CR22) 2021; 33 P Tseng (668_CR31) 2001; 109 MC Mukkamala (668_CR53) 2020; 2 |
| References_xml | – volume: 423 year: 2023 ident: 668_CR44 publication-title: J. Comput. Appl. Math. doi: 10.1016/j.cam.2022.114948 – volume: 31 start-page: 167 issue: 3 year: 2003 ident: 668_CR42 publication-title: Oper. Res. Lett. doi: 10.1016/S0167-6377(02)00231-6 – ident: 668_CR3 – volume: 51 start-page: 455 issue: 3 year: 2009 ident: 668_CR32 publication-title: SIAM Rev. doi: 10.1137/07070111X – volume: 2 start-page: 1066 year: 2019 ident: 668_CR17 publication-title: SIAM J. Math. Data Sci doi: 10.1137/19M1266265 – volume: 27 start-page: 372 issue: 2 year: 1983 ident: 668_CR60 publication-title: Soviet Math. Dokl. – volume: 19 start-page: 1574 issue: 4 year: 2009 ident: 668_CR56 publication-title: SIAM J. Optim. doi: 10.1137/070704277 – volume: 27 start-page: 1646 year: 2014 ident: 668_CR58 publication-title: Adv. Neural Inf. Process. Syst. – volume: 14 start-page: 1932 issue: 4 year: 2021 ident: 668_CR49 publication-title: SIAM J. Imag. Sci. doi: 10.1137/20M1387213 – volume: 14 start-page: 285 issue: 3 year: 2000 ident: 668_CR2 publication-title: J. Chemom. doi: 10.1002/1099-128X(200005/06)14:3<285::AID-CEM584>3.0.CO;2-1 – volume: 49 start-page: 499 issue: 5 year: 1952 ident: 668_CR30 publication-title: Psychol. Bull. doi: 10.1037/h0054245 – volume: 29 start-page: 203 issue: 1 year: 2015 ident: 668_CR24 publication-title: Data Min. Knowl. Discov. doi: 10.1007/s10618-013-0341-y – volume: 9 start-page: 267 issue: 4 year: 1944 ident: 668_CR29 publication-title: Psychometrika doi: 10.1007/BF02288739 – volume: 34 start-page: 126 issue: 1 year: 2013 ident: 668_CR15 publication-title: SIAM J. Matrix Anal. Appl. doi: 10.1137/100808034 – volume: 17 start-page: 433 issue: 3 year: 2021 ident: 668_CR43 publication-title: Pac. J. Optim. – volume: 1 start-page: 288 issue: 4 year: 2019 ident: 668_CR39 publication-title: INFORMS J. Optim. doi: 10.1287/ijoo.2018.0008 – volume: 20 start-page: 4 issue: 1 year: 2022 ident: 668_CR50 publication-title: Sampl. Theory Signal Process. Data Anal. doi: 10.1007/s43670-022-00021-x – volume: 68 start-page: 2170 year: 2020 ident: 668_CR48 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.2982321 – volume: 70 start-page: 1803 year: 2022 ident: 668_CR40 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2022.3163896 – volume: 7 start-page: 39 issue: 1–4 year: 1928 ident: 668_CR28 publication-title: J. Math. Phys. doi: 10.1002/sapm19287139 – ident: 668_CR21 – volume: 62 start-page: 133 issue: 1 year: 2020 ident: 668_CR16 publication-title: SIAM Rev. doi: 10.1137/18M1203626 – volume: 28 start-page: 2131 issue: 3 year: 2018 ident: 668_CR35 publication-title: SIAM J. Optim. doi: 10.1137/17M1138558 – ident: 668_CR36 – volume: 73 start-page: 431 issue: 3 year: 2008 ident: 668_CR1 publication-title: Psychometrika doi: 10.1007/s11336-008-9056-1 – volume: 39 start-page: 876 issue: 2 year: 2018 ident: 668_CR34 publication-title: SIAM J. Matrix Anal. Appl. doi: 10.1137/17M1112303 – ident: 668_CR63 – volume: 10 start-page: 1 year: 2022 ident: 668_CR8 publication-title: J. Oper. Res. Soc. China doi: 10.1007/s40305-021-00368-3 – volume: 61 start-page: 4834 issue: 19 year: 2013 ident: 668_CR12 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2013.2269903 – volume: 189 start-page: 66 year: 2023 ident: 668_CR64 publication-title: Appl. Numer. Math. doi: 10.1016/j.apnum.2023.03.014 – ident: 668_CR5 – volume: 68 start-page: 1792 year: 2020 ident: 668_CR23 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.2975353 – volume: 6 start-page: 164 issue: 1–4 year: 1927 ident: 668_CR27 publication-title: J. Math. Phys. doi: 10.1002/sapm192761164 – volume: 21 start-page: 38 issue: 1 year: 2020 ident: 668_CR18 publication-title: J. Mach. Learn. Res. – volume: 2 start-page: 658 issue: 3 year: 2020 ident: 668_CR53 publication-title: SIAM J. Math. Data Sci. doi: 10.1137/19M1298007 – ident: 668_CR47 doi: 10.1609/aaai.v38i14.29485 – volume: 64 start-page: 5052 issue: 19 year: 2016 ident: 668_CR11 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2016.2576427 – volume: 13 start-page: 381 issue: 1 year: 2020 ident: 668_CR26 publication-title: SIAM J. Imag. Sci. doi: 10.1137/19M1271750 – volume: 25 start-page: 856 issue: 2 year: 2015 ident: 668_CR41 publication-title: SIAM J. Optim. doi: 10.1137/130936361 – ident: 668_CR62 – volume: 26 start-page: 1551 issue: 10 year: 2019 ident: 668_CR51 publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2019.2938663 – volume: 146 start-page: 459 issue: 1–2 year: 2014 ident: 668_CR9 publication-title: Math. Program. doi: 10.1007/s10107-013-0701-9 – volume: 4 start-page: 1 issue: 5 year: 1964 ident: 668_CR45 publication-title: USSR Comput. Math. Math. Phys. doi: 10.1016/0041-5553(64)90137-5 – volume: 28 start-page: 333 issue: 1 year: 2018 ident: 668_CR54 publication-title: SIAM J. Optim. doi: 10.1137/16M1099546 – volume-title: First-Order and Stochastic Optimization Methods for Machine Learning year: 2020 ident: 668_CR55 doi: 10.1007/978-3-030-39568-1 – volume: 38 start-page: 914 issue: 5 year: 2023 ident: 668_CR46 publication-title: Optim. Methods. Softw. doi: 10.1080/10556788.2023.2189717 – ident: 668_CR37 doi: 10.1137/18M1178244 – volume: 92 start-page: 708 year: 2009 ident: 668_CR33 publication-title: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. doi: 10.1587/transfun.E92.A.708 – volume: 35 start-page: 283 issue: 3 year: 1970 ident: 668_CR6 publication-title: Psychometrika doi: 10.1007/BF02310791 – volume: 68 start-page: 4454 year: 2020 ident: 668_CR19 publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.3010719 – volume: 33 start-page: 3117 issue: 8 year: 2021 ident: 668_CR22 publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2019.2962031 – volume: 9 start-page: 1756 issue: 4 year: 2016 ident: 668_CR10 publication-title: SIAM J. Imag. Sci. doi: 10.1137/16M1064064 – ident: 668_CR61 – ident: 668_CR59 – volume: 23 start-page: 393 year: 2009 ident: 668_CR13 publication-title: J. Chemom. doi: 10.1002/cem.1236 – volume: 23 start-page: 432 year: 2009 ident: 668_CR4 publication-title: J. Chemom. doi: 10.1002/cem.1244 – volume: 23 start-page: 695 issue: 2 year: 2013 ident: 668_CR14 publication-title: SIAM J. Optim. doi: 10.1137/120868323 – ident: 668_CR20 doi: 10.1109/ACSSC.2017.8335432 – volume: 109 start-page: 475 year: 2001 ident: 668_CR31 publication-title: J. Optim. Theory Appl. doi: 10.1023/A:1017501703105 – ident: 668_CR38 – volume: 6 start-page: 1758 issue: 3 year: 2013 ident: 668_CR7 publication-title: SIAM J. Imag. Sci. doi: 10.1137/120887795 – volume: 33 start-page: 1272 issue: 4 year: 2012 ident: 668_CR25 publication-title: SIAM J. Matrix Anal. Appl. doi: 10.1137/110859063 – volume: 42 start-page: 330 issue: 2 year: 2017 ident: 668_CR52 publication-title: Math. Oper. Res. doi: 10.1287/moor.2016.0817 – volume: 32 start-page: 2230 issue: 3 year: 2022 ident: 668_CR57 publication-title: SIAM J. Optim. doi: 10.1137/21M140376X |
| SSID | ssj0009732 |
| Score | 2.4038339 |
| Snippet | The majority of classic tensor CP decomposition models are designed for squared loss, utilizing Euclidean distance as a local proximal term. However, the... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Index Database |
| StartPage | 201 |
| SubjectTerms | Algorithms Binary data Convergence Decomposition Euclidean geometry Lipschitz condition Tensors |
| Title | Inertial accelerated stochastic mirror descent for large-scale generalized tensor CP decomposition |
| URI | https://www.proquest.com/docview/3180761010 |
| Volume | 91 |
| WOSCitedRecordID | wos001423026400001&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: SpringerLINK Contemporary 1997-Present 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/eLvHCXMwlV3LSsNAFL2U4kIXvsVqlVm404F0Hk2ylGJRkFLwQXdhnlrQtKRVxK93bpJSC7roOpMhnDuZe2bm3DMAF0x4KZyOqUiMp8LFjmplFLVee4c1PqoqFL6PB4NkNEqHDbj69wQfi9wkynqYpJgfE4qMsdOtirUenpcOu3F5G1mUsi4NWZzXFTJ_d7GahVYn4TKz9HfW-6Zd2K4ZJLmuQr4HDZfvw9YvX8ED0Hc5yqVDK2VMyCtoB2FJoHnmVaEvM3kfF8WkILbyciKBuJI3lITTWQiZIy-VF_X4O7yFCvfwuDcMrVF_Xou8DuGpf_PYu6X1ZQrUBIY1p9YlLI48t4Y53e1oI3RqZRpxbrXAhZftGOsl88pZibZ8kUl0oBc6SY1VLuJH0MwnuTsGYiW3sVFx6ngiuOcqQKKF9F4Yw7S3LbhcgJtNK8-MbOmOjMhlAbmsRC77akF7gX9W_z-zLMw0uMESFosna3V2CpusjAoqEtvQnBcf7gw2zOd8PCvOywHzA5_cvBw |
| 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=Inertial+accelerated+stochastic+mirror+descent+for+large-scale+generalized+tensor+CP+decomposition&rft.jtitle=Computational+optimization+and+applications&rft.date=2025-05-01&rft.pub=Springer+Nature+B.V&rft.issn=0926-6003&rft.eissn=1573-2894&rft.volume=91&rft.issue=1&rft.spage=201&rft.epage=233&rft_id=info:doi/10.1007%2Fs10589-025-00668-x&rft.externalDBID=HAS_PDF_LINK |
| 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 |