Implementable tensor methods in unconstrained convex optimization

In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its ac...

Full description

Saved in:

Bibliographic Details
Published in:	Mathematical programming Vol. 186; no. 1-2; pp. 157 - 183
Main Author:	Nesterov, Yurii
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2021 Springer Nature B.V
Subjects:	Calculus of Variations and Optimal Control; Optimization Combinatorics Computational geometry Convergence Convex analysis Convexity Full Length Paper Iterative methods Lower bounds Mathematical analysis Mathematical and Computational Physics Mathematical Methods in Physics Mathematics Mathematics and Statistics Mathematics of Computing Numerical Analysis Optimization Polynomials Sequences Smoothness Tensors Theoretical 65K05 High-order methods Convex optimization 90C25 Lower complexity bounds 90C06 Worst-case complexity bounds Tensor methods
ISSN:	0025-5610, 1436-4646
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330–348, 2017; Lu et al. in SIOPT 28(1):333–354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level O 1 k 4 , where k is the number of iterations. This is very close to the lower bound of the order O 1 k 5 , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods.
AbstractList	In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330–348, 2017; Lu et al. in SIOPT 28(1):333–354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level $$O\left( {1 \over k^4}\right) $$ O 1 k 4 , where k is the number of iterations. This is very close to the lower bound of the order $$O\left( {1 \over k^5}\right) $$ O 1 k 5 , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods. In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330–348, 2017; Lu et al. in SIOPT 28(1):333–354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level O 1 k 4 , where k is the number of iterations. This is very close to the lower bound of the order O 1 k 5 , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods. In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330-348, 2017; Lu et al. in SIOPT 28(1):333-354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level , where is the number of iterations. This is very close to the lower bound of the order , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods. In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330-348, 2017; Lu et al. in SIOPT 28(1):333-354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level O 1 k 4 , where k is the number of iterations. This is very close to the lower bound of the order O 1 k 5 , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods.In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330-348, 2017; Lu et al. in SIOPT 28(1):333-354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level O 1 k 4 , where k is the number of iterations. This is very close to the lower bound of the order O 1 k 5 , which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods. In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330–348, 2017; Lu et al. in SIOPT 28(1):333–354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level O1k4, where k is the number of iterations. This is very close to the lower bound of the order O1k5, which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods. In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial. We analyze the simplest scheme, based on minimization of a regularized local model of the objective function, and its accelerated version obtained in the framework of estimating sequences. Their rates of convergence are compared with the worst-case lower complexity bounds for corresponding problem classes. Finally, for the third-order methods, we suggest an efficient technique for solving the auxiliary problem, which is based on the recently developed relative smoothness condition (Bauschke et al. in Math Oper Res 42:330–348, 2017; Lu et al. in SIOPT 28(1):333–354, 2018). With this elaboration, the third-order methods become implementable and very fast. The rate of convergence in terms of the function value for the accelerated third-order scheme reaches the level $$O\left( {1 \over k^4}\right) $$ O1k4, where k is the number of iterations. This is very close to the lower bound of the order $$O\left( {1 \over k^5}\right) $$ O1k5, which is also justified in this paper. At the same time, in many important cases the computational cost of one iteration of this method remains on the level typical for the second-order methods.
Author	Nesterov, Yurii
Author_xml	– sequence: 1 givenname: Yurii orcidid: 0000-0002-0542-8757 surname: Nesterov fullname: Nesterov, Yurii email: Yurii.Neterov@uclouvain.be organization: Center for Operations Research and Econometrics (CORE), Catholic University of Louvain (UCL)
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33627889$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUFPHSEUhUljU5-2f6CLZpJu3IyFAQbYNDEvtpqYdNOuCTB3FDMDr8AY7a8vz6e1unBBIOE7J-fec4D2QgyA0EeCjwnG4ksmmGDRYqLqYUy15A1aEUb7lvWs30MrjDve8p7gfXSQ8zXGmFAp36F9SvtOSKlW6OR83kwwQyjGTtAUCDmmZoZyFYfc-NAswcWQSzI-wNDU9w3cNnFT_Oz_mOJjeI_ejmbK8OHhPkS_vp3-XJ-1Fz--n69PLlrHGS4tt8wyY8gAPRkVw5wwC73hbhyUHY1ihBrBhg4PY0d6BlI6AZ1V1nEKykp6iL7ufDeLnWFwNXIyk94kP5t0p6Px-vlP8Ff6Mt5oIQWXfGtw9GCQ4u8FctGzzw6myQSIS9YdU5RxgQWt6OcX6HVcUqjjVUpKojohtoaf_k_0L8rjdisgd4BLMecEo3a-3C9tu89JE6y3RepdkboWqe-L1KRKuxfSR_dXRXQnyhUOl5CeYr-i-gs4UbGG
CitedBy_id	crossref_primary_10_1080_10556788_2023_2261604 crossref_primary_10_4236_jamp_2025_133047 crossref_primary_10_1134_S096554252101005X crossref_primary_10_1080_10556788_2021_2022148 crossref_primary_10_1155_2021_8826868 crossref_primary_10_1007_s10589_023_00533_9 crossref_primary_10_1134_S0965542524702208 crossref_primary_10_1007_s10898_022_01151_1 crossref_primary_10_1007_s10957_022_02062_7 crossref_primary_10_1007_s11075_024_01965_y crossref_primary_10_1007_s10107_024_02176_y crossref_primary_10_1080_10556788_2020_1818082 crossref_primary_10_1137_20M134705X crossref_primary_10_1137_19M130858X crossref_primary_10_1134_S096554252570071X crossref_primary_10_1007_s10107_023_02041_4 crossref_primary_10_1007_s10208_021_09499_8 crossref_primary_10_1080_10556788_2020_1731749 crossref_primary_10_1137_23M1593000 crossref_primary_10_1080_10556788_2023_2296443 crossref_primary_10_1137_22M1519444 crossref_primary_10_1134_S0965542524700076 crossref_primary_10_1137_21M1410063 crossref_primary_10_1007_s10107_021_01721_3 crossref_primary_10_1137_22M1488752 crossref_primary_10_1007_s10957_024_02383_9 crossref_primary_10_1137_22M1480872 crossref_primary_10_1080_10556788_2023_2256447 crossref_primary_10_1137_23M1585258 crossref_primary_10_1007_s10107_025_02270_9 crossref_primary_10_1007_s10107_021_01727_x crossref_primary_10_1007_s40305_022_00398_5 crossref_primary_10_1287_moor_2022_1343 crossref_primary_10_1137_21M1395764 crossref_primary_10_1007_s10107_025_02235_y crossref_primary_10_1007_s10589_021_00273_8 crossref_primary_10_1007_s10013_024_00720_z crossref_primary_10_1007_s10107_024_02075_2 crossref_primary_10_1016_j_aim_2024_109808 crossref_primary_10_1007_s10957_021_01838_7 crossref_primary_10_1007_s10957_021_01930_y crossref_primary_10_3390_math13081319 crossref_primary_10_1142_S0217595923400080
Cites_doi	10.1007/s10107-009-0286-5 10.1007/s10107-014-0794-9 10.1137/110833786 10.1080/10556788.2011.602076 10.1007/s10107-009-0337-y 10.1137/1.9780898717761 10.1145/962437.962438 10.1007/s10107-014-0790-0 10.1137/16M1106316 10.1287/moor.2016.0817 10.1007/s10107-004-0552-5 10.1007/BF00933151 10.1137/1.9780898719857 10.1137/1.9781611970791 10.1007/s11590-019-01395-z 10.1007/s10107-006-0706-8 10.1007/s10107-016-1065-8 10.1007/s10107-012-0629-5 10.1007/s10107-006-0089-x 10.1007/s10107-014-0753-5 10.1137/0801020 10.1007/978-1-4419-8853-9 10.1080/10556780903239071 10.1137/16M1087801 10.1137/16M1099546
ContentType	Journal Article
Copyright	The Author(s) 2019 The Author(s) 2019. The Author(s) 2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2019 – notice: The Author(s) 2019. – notice: The Author(s) 2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 5PM
DOI	10.1007/s10107-019-01449-1
DatabaseName	SpringerOpen CrossRef PubMed 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 MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef PubMed 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 MEDLINE - Academic
DatabaseTitleList	CrossRef PubMed MEDLINE - Academic Computer and Information Systems Abstracts
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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Mathematics
EISSN	1436-4646
EndPage	183
ExternalDocumentID	PMC7875858 33627889 10_1007_s10107_019_01449_1
Genre	Journal Article
GrantInformation_xml	– fundername: Russian Science Foundation grantid: 17-11-01027 funderid: http://dx.doi.org/10.13039/501100006769 – fundername: European Research Council grantid: 788368 funderid: http://dx.doi.org/10.13039/501100000781 – fundername: ; grantid: 788368 – fundername: ; grantid: 17-11-01027
GroupedDBID	--K --Z -52 -5D -5G -BR -EM -Y2 -~C -~X .4S .86 .DC .VR 06D 0R~ 0VY 199 1B1 1N0 1OL 1SB 203 28- 29M 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 7WY 88I 8AO 8FE 8FG 8FL 8TC 8UJ 8VB 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDBF ABDZT ABECU ABFTV ABHLI ABHQN ABJCF ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACNCT ACOKC ACOMO ACPIV ACUHS ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMOZ AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFFNX AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHQJS AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ AKVCP ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. B0M BA0 BAPOH BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS C6C CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EAD EAP EBA EBLON EBR EBS EBU ECS EDO EIOEI EJD EMI EMK EPL ESBYG EST ESX FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GROUPED_ABI_INFORM_COMPLETE GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ H~9 I-F I09 IAO 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 LAS LLZTM M0C M0N M2P M4Y M7S MA- N2Q N9A NB0 NDZJH NPVJJ NQ- NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P62 P9R PF0 PQBIZ PQBZA PQQKQ PROAC PT4 PT5 PTHSS Q2X QOK QOS QWB R4E R89 R9I RHV RIG RNI RNS ROL RPX RPZ RSV 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 TH9 TN5 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WH7 WK8 XPP YLTOR Z45 Z5O Z7R Z7S Z7X Z7Y Z7Z Z81 Z83 Z86 Z88 Z8M Z8N Z8R Z8T Z8W Z92 ZL0 ZMTXR ZWQNP ~02 ~8M ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADXHL AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP AMVHM ATHPR AYFIA CITATION PHGZM PHGZT PQGLB NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 5PM
ID	FETCH-LOGICAL-c540t-5b4b4aa1de61f940514be6a5cfd9bfa9413a74d20df2164e88c7e2b9bc53e9b83
IEDL.DBID	RSV
ISICitedReferencesCount	73
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000574702200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0025-5610
IngestDate	Tue Nov 04 01:52:48 EST 2025 Thu Oct 02 11:27:10 EDT 2025 Thu Sep 25 00:56:00 EDT 2025 Mon Jul 21 06:05:56 EDT 2025 Sat Nov 29 03:34:01 EST 2025 Tue Nov 18 21:59:56 EST 2025 Fri Feb 21 02:48:36 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1-2
Keywords	65K05 High-order methods Convex optimization 90C25 Lower complexity bounds 90C06 Worst-case complexity bounds Tensor methods
Language	English
License	The Author(s) 2019. Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c540t-5b4b4aa1de61f940514be6a5cfd9bfa9413a74d20df2164e88c7e2b9bc53e9b83
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-0542-8757
OpenAccessLink	https://link.springer.com/10.1007/s10107-019-01449-1
PMID	33627889
PQID	2488192778
PQPubID	25307
PageCount	27
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_7875858 proquest_miscellaneous_2493457073 proquest_journals_2488192778 pubmed_primary_33627889 crossref_citationtrail_10_1007_s10107_019_01449_1 crossref_primary_10_1007_s10107_019_01449_1 springer_journals_10_1007_s10107_019_01449_1
PublicationCentury	2000
PublicationDate	2021-03-01
PublicationDateYYYYMMDD	2021-03-01
PublicationDate_xml	– month: 03 year: 2021 text: 2021-03-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg – name: Netherlands – name: Heidelberg
PublicationSubtitle	A Publication of the Mathematical Optimization Society
PublicationTitle	Mathematical programming
PublicationTitleAbbrev	Math. Program
PublicationTitleAlternate	Math Program
PublicationYear	2021
Publisher	Springer Berlin Heidelberg Springer Nature B.V
Publisher_xml	– name: Springer Berlin Heidelberg – name: Springer Nature B.V
References	BirginEGGardenghiJLMartinesJMSantosSATointPhLWorst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularization modelsMath. Program.2017163359368363298310.1007/s10107-016-1065-8 NesterovYuSmooth minimization of non-smooth functionsMath. Program.20051031127152216653710.1007/s10107-004-0552-5 Birgin, E.G., Gardenghi, J.L., Martines, J.M., Santos, S.A.: Remark on Algorithm 566: Modern Fortran Routines for Testing Unconsrained Optimization Software with Derivatives up to Third-Order. Technical report, Department of Computer Sciences, University of Sao Paolo, Brazil (2018) NesterovYuIntroductory Lectures on Convex Optimization2004BostonKluwer10.1007/978-1-4419-8853-9 CartisCGouldNIMTointPhLUniversal regularization methods–varying the power, the smoothness and the accuracySIAM. J. Optim.2019291595615391941010.1137/16M1106316 NesterovYuAccelerating the cubic regularization of Newton’s method on convex problemsMath. Program.20081121159181232700510.1007/s10107-006-0089-x CartisCGouldNIMTointPhLAdaptive cubic overestimation methods for unconstrained optimization. Part II: worst-case function evaluation complexity.Math. Program.20111272245295277670110.1007/s10107-009-0286-5 Carmon, Y., Duchi, J.C., Hinder, O., Sidford, A.: Lower bounds for finding stationary points II. Archiv (2017). arXiv:1711.00841 HoffmannKHKornstaedtHJHigher-order necessary conditions in abstract mathematical programmingJOTA19782653356852665210.1007/BF00933151 NesterovYuGradient methods for minimizing composite functionsMath. Program.20131401125161307186510.1007/s10107-012-0629-5 GrapigliaGNNesterovYuRegularized Newton methods for minimizing functions with Hölder continuous HessiansSIOPT201727147850610.1137/16M1087801 NesterovYuPolyakBCubic regularization of Newton’s method and its global performanceMath. Program.20061081177205222945910.1007/s10107-006-0706-8 CartisCGouldNIMTointPhLAdaptive cubic overestimation methods for unconstrained optimization. Part I: motivation, convergence and numerical resultsMath. Program.2012130229531910.1007/s10107-009-0337-y GouldNIMOrbanDTointPhLGALAHAD, a library of thread-safe Fortran 90 packages for large-scale nonlinear optimizationACM Trans. Math. Softw.2003294353372207733710.1145/962437.962438 BianWChenXYeYComplexity analysis of interior-point algorithms for non-Lipschitz and non-convex minimizationMath. Program.201513930132710.1007/s10107-014-0753-5 GrapigliaGNYuanJYuanYOn the convergence and worst-case complexity of trust-region and regularization methods for unconstrained optimizationMath. Program.2015152491520336949010.1007/s10107-014-0794-9 GundersenGSteihaugTOn large-scale unconstrained optimization problems and higher order methodsOptim. Methods. Softw.2010253337358273883110.1080/10556780903239071 NesterovYuNemirovskiiAInterior Point Polynomial Methods in Convex Programming: Theory and Applications1994PhiladelphiaSIAM10.1137/1.9781611970791 SchnabelRBChowTTTensor methods for unconstrained optimization using second derivativesSIAM J. Optim.199113293315111252210.1137/0801020 BauschkeHHBolteJTeboulleMA descent lemma beyond Lipschitz gradient continuety: first-order methods revisited and applicationsMath. Oper. Res.201742330348365199410.1287/moor.2016.0817 CartisCGouldNIMTointPhLEvaluation complexity of adaptive cubic regularization methods for convex unconstrained optimizationOptim. Methods Softw.2012272197219290195710.1080/10556788.2011.602076 Arjevani, Y., Shamir, O., Shiff, R.: Oracle Complexity of Second-Order Methods for Smooth Convex Optimization (2017). arXiv:1705.07260 [math.OC] Agarwal, N., Hazan, E.: Lower Bounds for Higher-Order Convex Optimization (2017). arXiv:1710.10329v1 [math.OC] Birgin, E.G., Gardenghi, J.L., Martines, J.M., Santos, S.A.: On the Use of Third-Order Models with Fourth-Order Regularization for Unconstrained Optimization. Technical report, Department of Computer Sciences, University of Sao Paolo, Brazil (2018) NesterovYuUniversal gradient methods for convex optimization problemsMath. Program.2015152381404336948610.1007/s10107-014-0790-0 Carmon, Y., Duchi, J.C., Hinder, O., Sidford, A.: Lower bounds for finding stationary points I. Archiv (2017). arXiv:1710.11606 GriewankAWaltherAEvaluating Derivatives: Principles and Techniques of Algorithmic Differentiation. Applied Mathematics20082PhiladelphiaSIAM10.1137/1.9780898717761 LuHFreundRNesterovYuRelatively smooth convex optimization by first-order methods, and applicationsSIOPT2018281333354375988110.1137/16M1099546 LasserreJBMoments, Positive Polynomials and Their Applications2010LondonImperial College Press1211.90007 ConnARGouldNIMTointPhLTrust Region Methods2000New YorkMOS-SIAM Series on Optimization10.1137/1.9780898719857 Baes, M.: Estimate sequence methods: extensions and approximations. Optim. Online (2009) MonteiroRDCSvaiterBFAn accelerated hybrid proximal extragradient method for convex optimization and its implications to second-order methodsSIOPT201323210921125306315110.1137/110833786 C Cartis (1449_CR11) 2012; 130 NIM Gould (1449_CR16) 2003; 29 RB Schnabel (1449_CR32) 1991; 1 Yu Nesterov (1449_CR28) 2013; 140 Yu Nesterov (1449_CR26) 2005; 103 C Cartis (1449_CR14) 2019; 29 GN Grapiglia (1449_CR17) 2017; 27 W Bian (1449_CR5) 2015; 139 C Cartis (1449_CR12) 2011; 127 Yu Nesterov (1449_CR25) 2004 Yu Nesterov (1449_CR30) 1994 Yu Nesterov (1449_CR31) 2006; 108 1449_CR1 HH Bauschke (1449_CR4) 2017; 42 1449_CR3 RDC Monteiro (1449_CR24) 2013; 23 1449_CR2 EG Birgin (1449_CR8) 2017; 163 H Lu (1449_CR21) 2018; 28 KH Hoffmann (1449_CR22) 1978; 26 A Griewank (1449_CR19) 2008 JB Lasserre (1449_CR23) 2010 AR Conn (1449_CR15) 2000 G Gundersen (1449_CR20) 2010; 25 Yu Nesterov (1449_CR29) 2015; 152 C Cartis (1449_CR13) 2012; 27 1449_CR7 1449_CR6 Yu Nesterov (1449_CR27) 2008; 112 1449_CR9 GN Grapiglia (1449_CR18) 2015; 152 1449_CR10
References_xml	– reference: NesterovYuGradient methods for minimizing composite functionsMath. Program.20131401125161307186510.1007/s10107-012-0629-5 – reference: NesterovYuSmooth minimization of non-smooth functionsMath. Program.20051031127152216653710.1007/s10107-004-0552-5 – reference: NesterovYuPolyakBCubic regularization of Newton’s method and its global performanceMath. Program.20061081177205222945910.1007/s10107-006-0706-8 – reference: ConnARGouldNIMTointPhLTrust Region Methods2000New YorkMOS-SIAM Series on Optimization10.1137/1.9780898719857 – reference: SchnabelRBChowTTTensor methods for unconstrained optimization using second derivativesSIAM J. Optim.199113293315111252210.1137/0801020 – reference: BianWChenXYeYComplexity analysis of interior-point algorithms for non-Lipschitz and non-convex minimizationMath. Program.201513930132710.1007/s10107-014-0753-5 – reference: NesterovYuUniversal gradient methods for convex optimization problemsMath. Program.2015152381404336948610.1007/s10107-014-0790-0 – reference: BauschkeHHBolteJTeboulleMA descent lemma beyond Lipschitz gradient continuety: first-order methods revisited and applicationsMath. Oper. Res.201742330348365199410.1287/moor.2016.0817 – reference: CartisCGouldNIMTointPhLAdaptive cubic overestimation methods for unconstrained optimization. Part I: motivation, convergence and numerical resultsMath. Program.2012130229531910.1007/s10107-009-0337-y – reference: GrapigliaGNYuanJYuanYOn the convergence and worst-case complexity of trust-region and regularization methods for unconstrained optimizationMath. Program.2015152491520336949010.1007/s10107-014-0794-9 – reference: Agarwal, N., Hazan, E.: Lower Bounds for Higher-Order Convex Optimization (2017). arXiv:1710.10329v1 [math.OC] – reference: NesterovYuIntroductory Lectures on Convex Optimization2004BostonKluwer10.1007/978-1-4419-8853-9 – reference: Baes, M.: Estimate sequence methods: extensions and approximations. Optim. Online (2009) – reference: NesterovYuAccelerating the cubic regularization of Newton’s method on convex problemsMath. Program.20081121159181232700510.1007/s10107-006-0089-x – reference: CartisCGouldNIMTointPhLAdaptive cubic overestimation methods for unconstrained optimization. Part II: worst-case function evaluation complexity.Math. Program.20111272245295277670110.1007/s10107-009-0286-5 – reference: LuHFreundRNesterovYuRelatively smooth convex optimization by first-order methods, and applicationsSIOPT2018281333354375988110.1137/16M1099546 – reference: Birgin, E.G., Gardenghi, J.L., Martines, J.M., Santos, S.A.: On the Use of Third-Order Models with Fourth-Order Regularization for Unconstrained Optimization. Technical report, Department of Computer Sciences, University of Sao Paolo, Brazil (2018) – reference: GouldNIMOrbanDTointPhLGALAHAD, a library of thread-safe Fortran 90 packages for large-scale nonlinear optimizationACM Trans. Math. Softw.2003294353372207733710.1145/962437.962438 – reference: HoffmannKHKornstaedtHJHigher-order necessary conditions in abstract mathematical programmingJOTA19782653356852665210.1007/BF00933151 – reference: CartisCGouldNIMTointPhLUniversal regularization methods–varying the power, the smoothness and the accuracySIAM. J. Optim.2019291595615391941010.1137/16M1106316 – reference: Arjevani, Y., Shamir, O., Shiff, R.: Oracle Complexity of Second-Order Methods for Smooth Convex Optimization (2017). arXiv:1705.07260 [math.OC] – reference: Carmon, Y., Duchi, J.C., Hinder, O., Sidford, A.: Lower bounds for finding stationary points I. Archiv (2017). arXiv:1710.11606 – reference: GriewankAWaltherAEvaluating Derivatives: Principles and Techniques of Algorithmic Differentiation. Applied Mathematics20082PhiladelphiaSIAM10.1137/1.9780898717761 – reference: Carmon, Y., Duchi, J.C., Hinder, O., Sidford, A.: Lower bounds for finding stationary points II. Archiv (2017). arXiv:1711.00841 – reference: Birgin, E.G., Gardenghi, J.L., Martines, J.M., Santos, S.A.: Remark on Algorithm 566: Modern Fortran Routines for Testing Unconsrained Optimization Software with Derivatives up to Third-Order. Technical report, Department of Computer Sciences, University of Sao Paolo, Brazil (2018) – reference: NesterovYuNemirovskiiAInterior Point Polynomial Methods in Convex Programming: Theory and Applications1994PhiladelphiaSIAM10.1137/1.9781611970791 – reference: GrapigliaGNNesterovYuRegularized Newton methods for minimizing functions with Hölder continuous HessiansSIOPT201727147850610.1137/16M1087801 – reference: MonteiroRDCSvaiterBFAn accelerated hybrid proximal extragradient method for convex optimization and its implications to second-order methodsSIOPT201323210921125306315110.1137/110833786 – reference: GundersenGSteihaugTOn large-scale unconstrained optimization problems and higher order methodsOptim. Methods. Softw.2010253337358273883110.1080/10556780903239071 – reference: LasserreJBMoments, Positive Polynomials and Their Applications2010LondonImperial College Press1211.90007 – reference: BirginEGGardenghiJLMartinesJMSantosSATointPhLWorst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularization modelsMath. Program.2017163359368363298310.1007/s10107-016-1065-8 – reference: CartisCGouldNIMTointPhLEvaluation complexity of adaptive cubic regularization methods for convex unconstrained optimizationOptim. Methods Softw.2012272197219290195710.1080/10556788.2011.602076 – volume: 127 start-page: 245 issue: 2 year: 2011 ident: 1449_CR12 publication-title: Math. Program. doi: 10.1007/s10107-009-0286-5 – volume: 152 start-page: 491 year: 2015 ident: 1449_CR18 publication-title: Math. Program. doi: 10.1007/s10107-014-0794-9 – volume: 23 start-page: 1092 issue: 2 year: 2013 ident: 1449_CR24 publication-title: SIOPT doi: 10.1137/110833786 – volume: 27 start-page: 197 issue: 2 year: 2012 ident: 1449_CR13 publication-title: Optim. Methods Softw. doi: 10.1080/10556788.2011.602076 – ident: 1449_CR2 – volume: 130 start-page: 295 issue: 2 year: 2012 ident: 1449_CR11 publication-title: Math. Program. doi: 10.1007/s10107-009-0337-y – volume-title: Evaluating Derivatives: Principles and Techniques of Algorithmic Differentiation. Applied Mathematics year: 2008 ident: 1449_CR19 doi: 10.1137/1.9780898717761 – volume: 29 start-page: 353 issue: 4 year: 2003 ident: 1449_CR16 publication-title: ACM Trans. Math. Softw. doi: 10.1145/962437.962438 – volume: 152 start-page: 381 year: 2015 ident: 1449_CR29 publication-title: Math. Program. doi: 10.1007/s10107-014-0790-0 – volume: 29 start-page: 595 issue: 1 year: 2019 ident: 1449_CR14 publication-title: SIAM. J. Optim. doi: 10.1137/16M1106316 – volume: 42 start-page: 330 year: 2017 ident: 1449_CR4 publication-title: Math. Oper. Res. doi: 10.1287/moor.2016.0817 – volume: 103 start-page: 127 issue: 1 year: 2005 ident: 1449_CR26 publication-title: Math. Program. doi: 10.1007/s10107-004-0552-5 – volume: 26 start-page: 533 year: 1978 ident: 1449_CR22 publication-title: JOTA doi: 10.1007/BF00933151 – volume-title: Trust Region Methods year: 2000 ident: 1449_CR15 doi: 10.1137/1.9780898719857 – ident: 1449_CR9 – volume-title: Interior Point Polynomial Methods in Convex Programming: Theory and Applications year: 1994 ident: 1449_CR30 doi: 10.1137/1.9781611970791 – ident: 1449_CR7 doi: 10.1007/s11590-019-01395-z – volume: 108 start-page: 177 issue: 1 year: 2006 ident: 1449_CR31 publication-title: Math. Program. doi: 10.1007/s10107-006-0706-8 – volume: 163 start-page: 359 year: 2017 ident: 1449_CR8 publication-title: Math. Program. doi: 10.1007/s10107-016-1065-8 – ident: 1449_CR3 – ident: 1449_CR1 – volume: 140 start-page: 125 issue: 1 year: 2013 ident: 1449_CR28 publication-title: Math. Program. doi: 10.1007/s10107-012-0629-5 – volume: 112 start-page: 159 issue: 1 year: 2008 ident: 1449_CR27 publication-title: Math. Program. doi: 10.1007/s10107-006-0089-x – volume: 139 start-page: 301 year: 2015 ident: 1449_CR5 publication-title: Math. Program. doi: 10.1007/s10107-014-0753-5 – volume: 1 start-page: 293 issue: 3 year: 1991 ident: 1449_CR32 publication-title: SIAM J. Optim. doi: 10.1137/0801020 – volume-title: Introductory Lectures on Convex Optimization year: 2004 ident: 1449_CR25 doi: 10.1007/978-1-4419-8853-9 – volume: 25 start-page: 337 issue: 3 year: 2010 ident: 1449_CR20 publication-title: Optim. Methods. Softw. doi: 10.1080/10556780903239071 – volume: 27 start-page: 478 issue: 1 year: 2017 ident: 1449_CR17 publication-title: SIOPT doi: 10.1137/16M1087801 – volume: 28 start-page: 333 issue: 1 year: 2018 ident: 1449_CR21 publication-title: SIOPT doi: 10.1137/16M1099546 – ident: 1449_CR10 – volume-title: Moments, Positive Polynomials and Their Applications year: 2010 ident: 1449_CR23 – ident: 1449_CR6
SSID	ssj0001388
Score	2.6070693
Snippet	In this paper we develop new tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex...
SourceID	pubmedcentral proquest pubmed crossref springer
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	157
SubjectTerms	Calculus of Variations and Optimal Control; Optimization Combinatorics Computational geometry Convergence Convex analysis Convexity Full Length Paper Iterative methods Lower bounds Mathematical analysis Mathematical and Computational Physics Mathematical Methods in Physics Mathematics Mathematics and Statistics Mathematics of Computing Numerical Analysis Optimization Polynomials Sequences Smoothness Tensors Theoretical
Title	Implementable tensor methods in unconstrained convex optimization
URI	https://link.springer.com/article/10.1007/s10107-019-01449-1 https://www.ncbi.nlm.nih.gov/pubmed/33627889 https://www.proquest.com/docview/2488192778 https://www.proquest.com/docview/2493457073 https://pubmed.ncbi.nlm.nih.gov/PMC7875858
Volume	186
WOSCitedRecordID	wos000574702200001&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: 1436-4646 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001388 issn: 0025-5610 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/eLvHCXMwnV1bT4MwFD7R6YM-eL-gc8HENyUZUGj7uBiNLy7GW_ZGKLRxyQQzNuPP97QDtjk10UfSQulpz6Xpd74DcBZqNynaygk1DQARnDsslcrhIfUEl4GiXJhiE7TbZb0evyuTwooK7V5dSRpLPZPs5hqYpMb3EMIdPPOsoLtjWh3vH55r--v6jFWFWnV0UKbKfP-NeXe0EGMuQiW_3JcaN3S9-b8JbMFGGXbanck-2YYlme3A-gwZIT7d1gyuxS50DG2wQZaLgbQ1zj0f2pN604Xdz2z0hzq01BUmZGob8PqHnaMBei0zO_fg6frq8fLGKcstOAmGbSMnEESQOHZTGbqKE02MLmQYB4lKuVAxR3cXU5J67VR5eMiSjCVU4oKKJPAlF8zfh0aWZ_IQbBYKqWmDPCUC4se-kIKEPhrlUKSuagcWuJXUo6TkItc_PIimLMpaWBEKKzLCilwLzut33iZMHL_2blaLGZVaWUQeWiuMaCllFpzWzahP-pIkzmQ-1n24TwKKls-Cg8na18P56O0pY9wCOrcr6g6aq3u-Jeu_GM5utIt4MMNxL6q9Mf2tn2dx9Lfux7DmaciNgcg1oTEajuUJrCbvo34xbMEy7bGW0ZVPYG0NFQ
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwED9kCuqD3x_VqRV808Lapk3yOERR3Ib4xd5K0yY40E7WKf75XrK22_wCfSy5Ns0lubuQ3_0O4CjUblI0lBNqGgAiOHdYKpXDQ-oJLgNFuTDFJminw7pdfl0kheUl2r28kjSWeiLZzTUwSY3vIYQ7eOaZJeixNJDv5vahsr-uz1hZqFVHB0WqzPffmHZHX2LMr1DJT_elxg2dL_9vACuwVISddnO0TlZhRmZrsDhBRohP7YrBNV-HpqENNshy8SRtjXPvD-xRvenc7mU2-kMdWuoKEzK1DXj93e6jAXouMjs34P787O70winKLTgJhm1DJxBEkDh2Uxm6ihNNjC5kGAeJSrlQMUd3F1OSeo1UeXjIkowlVOKEiiTwJRfM34Ra1s_kNtgsFFLTBnlKBMSPfSEFCX00yqFIXdUILHBLrUdJwUWuf_gpGrMoa2VFqKzIKCtyLTiu3nkZMXH8Kl0vJzMqdmUeeWitMKKllFlwWDXjftKXJHEm-69ahvskoGj5LNgazX3VnY_enjLGLaBTq6IS0Fzd0y1Z79FwdqNdxIMZ9ntSro3xb_08ip2_iR_A_MVduxW1LjtXu7DgafiNgcvVoTYcvMo9mEvehr18sG92zAetiw8R
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ba9swFD6UdIz1oVt3ad2lqwd720xjW7akx7AtdLQLgV3Im7FsiQVSJ8RJ6c_vOfIlybIVxh6NZMuSjs4Ffec7AO9iMpOqZ7yYaACYktITuTaejHmgpI4Ml8oWm-DDoRiP5Wgji9-i3ZsrySqngViaiuXFPDcXG4lvvoVMEtaHMelh_LPPqGgQxevffra62A-FaIq2kqdQp838-RvbpmnH39yFTf52d2pN0uDp_0_mGRzW7qjbr-TnCPZ08RwONkgK8elry-xavoC-pRO2iHM11S7h32cLt6pDXbqTwkU7SS4nVZ7QuWtB7XfuDBXTTZ3x-RJ-DD5__3jp1WUYvAzduaUXKaZYmvq5jn0jGRGmKx2nUWZyqUwq0QymnOVBLzcBBl9aiIxr3GiVRaGWSoSvoFPMCn0CroiVJjqhwKiIhWmotGJxiMo6VrlvepEDfrMDSVZzlNMPT5M1uzItVoKLldjFSnwH3rfvzCuGjgd7d5uNTerTWiYBajH0dDkXDrxtm_Gc0eVJWujZivrIkEUcNaIDx5UctMOF6AVwIaQDfEtC2g7E4b3dUkx-WS5v1JcYsOG4Hxo5Wf_W32dx-m_dz-Hx6NMguf4yvHoNTwJC5VgUXRc6y8VKn8Gj7HY5KRdv7OG5B9SBF_U
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=Implementable+tensor+methods+in+unconstrained+convex+optimization&rft.jtitle=Mathematical+programming&rft.au=Nesterov%2C+Yurii&rft.date=2021-03-01&rft.issn=0025-5610&rft.volume=186&rft.issue=1&rft.spage=157&rft_id=info:doi/10.1007%2Fs10107-019-01449-1&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0025-5610&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0025-5610&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0025-5610&client=summon