Learn to optimize—a brief overview

Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are alrea...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:National science review Ročník 11; číslo 8; s. nwae132
Hlavní autori: Tang, Ke, Yao, Xin
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: China Oxford University Press 01.08.2024
Predmet:
ISSN:2095-5138, 2053-714X, 2053-714X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as learn to optimize and reviews the progress achieved. The article presents an overview on “Learn to Optimiz”, a paradigm that leverage on a set of training instances to accelerate the tedious configuration process of optimization algorithms.
AbstractList Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as and reviews the progress achieved.
Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as learn to optimize and reviews the progress achieved.Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as learn to optimize and reviews the progress achieved.
Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as learn to optimize and reviews the progress achieved.
Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a problem instance, a trial-and-error configuration process is required, which is very costly and even prohibitive for problems that are already computationally intensive, e.g. optimization problems associated with machine learning tasks. In the past decades, many studies have been conducted to accelerate the tedious configuration process by learning from a set of training instances. This article refers to these studies as learn to optimize and reviews the progress achieved. The article presents an overview on “Learn to Optimiz”, a paradigm that leverage on a set of training instances to accelerate the tedious configuration process of optimization algorithms.
Author Tang, Ke
Yao, Xin
Author_xml – sequence: 1
  givenname: Ke
  surname: Tang
  fullname: Tang, Ke
  email: tangk3@sustech.edu.cn
– sequence: 2
  givenname: Xin
  surname: Yao
  fullname: Yao, Xin
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39007005$$D View this record in MEDLINE/PubMed
BookMark eNp90M9Kw0AQBvBFKrbWnrxLDiKCxM5ms5vkKMV_UPCi4G3Z3U5gIcnG3bRFTz6ET-iTmNL2IuJp5vD7BuY7JoPGNUjIKYVrCgWbNsFPm7VCypIDMkqAszij6etgsxc85pTlQzIJwWrod5FlKT0iQ1YAZAB8RM7nqHwTdS5ybWdr-4Hfn18q0t5iGbkV-pXF9Qk5LFUVcLKbY_Jyd_s8e4jnT_ePs5t5bBjPujjlFHORCmMWKEDohJaF0KgwKTHjChaGsZzqBIxhgiWam9RACWkCme6hZmNyub3beve2xNDJ2gaDVaUadMsgGeQgGBdZ0dOzHV3qGhey9bZW_l3uP-sB3QLjXQgeS2lspzrrms4rW0kKclOg7AuUuwL7zNWvzP7s3_piq92y_Rf-AM6Ff_U
CitedBy_id crossref_primary_10_1016_j_aei_2025_103428
crossref_primary_10_1016_j_swevo_2024_101838
crossref_primary_10_1016_j_knosys_2025_114355
crossref_primary_10_1093_nsr_nwae288
crossref_primary_10_1109_TCYB_2025_3535777
crossref_primary_10_1038_s41467_025_62997_z
crossref_primary_10_3390_sym16081030
crossref_primary_10_1016_j_neucom_2025_130633
crossref_primary_10_1109_TAI_2025_3545792
Cites_doi 10.1007/978-981-19-5650-8
10.1145/1456650.1456656
10.1016/j.ins.2014.03.105
10.1109/TEVC.2021.3108185
10.1609/aiide.v13i1.12927
10.1109/TEVC.2022.3232776
10.1007/978-1-4419-1665-5
10.1162/106365601750190398
10.1609/aaai.v24i1.7565
10.1016/j.ejor.2020.07.063
10.1016/j.neucom.2016.04.027
10.1016/j.eswa.2020.113613
10.1109/ICTAI.2014.18
10.1109/TITS.2020.3018903
10.1016/j.orp.2016.09.002
10.1609/aimag.v35i3.2460
10.1360/SST-2021-0372
10.1162/evco_a_00215
10.1126/science.275.5296.51
10.1162/evco_a_00242
10.1109/TSSC.1968.300136
10.1016/j.swevo.2021.100927
10.1007/978-3-642-35289-8_25
10.48550/arXiv.2103.12828
10.1007/s10732-010-9126-2
10.24963/ijcai.2017/281
10.1609/aaai.v37i7.26064
10.1016/j.cor.2015.04.022
10.1007/978-981-13-5956-9
10.1007/978-3-642-25566-3_40
10.1080/00207543.2011.653010
10.1007/s00500-022-07118-4
10.1016/j.artint.2013.10.003
10.1145/3205455.3205585
10.48550/arXiv.1606.04474
10.1016/j.artint.2015.11.002
10.1023/B:MACH.0000015879.28004.9b
10.1007/978-3-662-04726-2
10.1109/IJCNN52387.2021.9533538
10.1109/CVPR52688.2022.00545
10.1007/978-3-642-04244-7_14
10.1609/aaai.v29i1.9640
10.1016/S0305-0548(96)00062-7
10.1007/978-3-642-13520-0_23
10.1038/scientificamerican0792-66
10.1145/3321707.3321845
10.1016/S0925-2312(00)00324-6
10.1109/TEVC.2021.3059661
10.1038/nature24270
10.1016/j.artint.2016.05.004
10.1145/3583133.3590697
10.1609/aaai.v34i03.5618
10.1613/jair.2861
10.1145/3067695.3082513
10.1145/3470918
10.1016/S0065-2458(08)60520-3
10.1137/15M1050276
10.1109/TCYB.2020.2984546
10.48550/arXiv.2109.09831
10.1145/1538902.1538906
10.1613/jair.1.13676
10.1109/MCI.2023.3277768
10.1145/3406325.3451036
10.1023/A:1026569813391
10.1609/aaai.v33i01.33011560
10.1016/0893-6080(88)90003-2
10.1016/j.orl.2022.01.018
10.1109/TEVC.2023.3278132
10.1109/TPAMI.2021.3079209
10.1287/opre.1050.0243
10.1609/aaai.v30i1.10170
10.1017/CBO9780511804441
10.1109/4235.585893
10.1038/s41586-021-03544-w
10.1109/SSCI51031.2022.10022078
ContentType Journal Article
Copyright The Author(s) 2024 Published by Oxford University Press on behalf of China Science Publishing & Media Ltd. 2024
The Author(s) 2024 Published by Oxford University Press on behalf of China Science Publishing & Media Ltd.
Copyright_xml – notice: The Author(s) 2024 Published by Oxford University Press on behalf of China Science Publishing & Media Ltd. 2024
– notice: The Author(s) 2024 Published by Oxford University Press on behalf of China Science Publishing & Media Ltd.
DBID TOX
AAYXX
CITATION
NPM
7X8
DOI 10.1093/nsr/nwae132
DatabaseName Oxford University Press Open Access
CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
CrossRef

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: TOX
  name: Oxford Journals Open Access Collection
  url: https://academic.oup.com/journals/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
EISSN 2053-714X
ExternalDocumentID 39007005
10_1093_nsr_nwae132
10.1093/nsr/nwae132
Genre Journal Article
Review
GroupedDBID -SA
-SC
-S~
0R~
4.4
5VR
AAFWJ
AAOGV
AAPXW
AAVAP
ABDBF
ABEJV
ABGNP
ABPTD
ABQLI
ABXVV
ACGFS
ACUHS
ADMLS
AENEX
AFPKN
AFUIB
ALMA_UNASSIGNED_HOLDINGS
AMNDL
AVWKF
BAYMD
CAJEA
CAJEC
CCEZO
CCVFK
CEKLB
EBS
EJD
ESX
FA0
GROUPED_DOAJ
H13
KSI
O9-
OK1
Q--
RPM
RXO
TOX
U1G
U5K
U5M
AAYXX
CITATION
AAXDM
AFULF
NPM
ROX
7X8
ID FETCH-LOGICAL-c357t-451e8646ccde606b21f96beae2fe75a0dc3381b20cc3632b5c4c0f04207b96bb3
IEDL.DBID TOX
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001221382600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2095-5138
2053-714X
IngestDate Fri Jul 11 08:30:09 EDT 2025
Wed Feb 19 02:04:05 EST 2025
Tue Nov 18 20:54:57 EST 2025
Sat Nov 29 02:00:30 EST 2025
Mon Jun 30 08:34:45 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 8
Keywords data-driven algorithm design
machine learning
optimization
automated algorithm configuration
Language English
License This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
https://creativecommons.org/licenses/by/4.0
The Author(s) 2024 Published by Oxford University Press on behalf of China Science Publishing & Media Ltd.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c357t-451e8646ccde606b21f96beae2fe75a0dc3381b20cc3632b5c4c0f04207b96bb3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
OpenAccessLink https://dx.doi.org/10.1093/nsr/nwae132
PMID 39007005
PQID 3080635679
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3080635679
pubmed_primary_39007005
crossref_citationtrail_10_1093_nsr_nwae132
crossref_primary_10_1093_nsr_nwae132
oup_primary_10_1093_nsr_nwae132
PublicationCentury 2000
PublicationDate 2024-08-01
PublicationDateYYYYMMDD 2024-08-01
PublicationDate_xml – month: 08
  year: 2024
  text: 2024-08-01
  day: 01
PublicationDecade 2020
PublicationPlace China
PublicationPlace_xml – name: China
PublicationTitle National science review
PublicationTitleAlternate Natl Sci Rev
PublicationYear 2024
Publisher Oxford University Press
Publisher_xml – name: Oxford University Press
References Arinze (2024071214370155300_bib33) 1997; 24
Zhao (2024071214370155300_bib35) 2021
Balcan (2024071214370155300_bib82) 2021
KhudaBukhsh (2024071214370155300_bib12) 2016; 232
Feng (2024071214370155300_bib25) 2023
Beham (2024071214370155300_bib38) 2017
Liu (2024071214370155300_bib67) 2023; 18
Gratch (2024071214370155300_bib50) 1992
Birattari (2024071214370155300_bib54) 2002
Langdon (2024071214370155300_bib18) 2002
Weisz (2024071214370155300_bib59) 2018
Kleinberg (2024071214370155300_bib80) 2019
Hutter (2024071214370155300_bib61) 2010
Wolpert (2024071214370155300_bib26) 1997; 1
Pihera (2024071214370155300_bib46) 2014
Hruby (2024071214370155300_bib87) 2022
Smith-Miles (2024071214370155300_bib84) 2015; 63
Santu (2024071214370155300_bib10) 2022; 54
Hospedales (2024071214370155300_bib21) 2022; 44
Schede (2024071214370155300_bib16) 2022; 75
Meunier (2024071214370155300_bib44) 2022; 26
Loreggia (2024071214370155300_bib47) 2016
Huberman (2024071214370155300_bib71) 1997; 275
Hansen (2024071214370155300_bib24) 2001; 9
Jiang (2024071214370155300_bib70) 2023
Tang (2024071214370155300_bib75) 2014; 279
Hutter (2024071214370155300_bib8) 2009; 36
Kostovska (2024071214370155300_bib45) 2023
Silver (2024071214370155300_bib63) 2017; 550
Beham (2024071214370155300_bib39) 2018
Liu (2024071214370155300_bib77) 2023; 53
Chen X and Tian (2024071214370155300_bib66) 2019
Zhan (2024071214370155300_bib69) 2023; 27
Chen (2024071214370155300_bib14) 2022; 23
Kerschke (2024071214370155300_bib34) 2018; 26
Holland (2024071214370155300_bib20) 1992; 267
Pfahringer (2024071214370155300_bib31) 2000
Bello (2024071214370155300_bib64) 2017
Bengio (2024071214370155300_bib13) 2021; 290
López-Ibáñez (2024071214370155300_bib55) 2016; 3
Liu (2024071214370155300_bib76) 2023
Balcan (2024071214370155300_bib83) 2017
Seipp (2024071214370155300_bib78) 2015
Mirhoseini (2024071214370155300_bib88) 2021; 594
Gendreau (2024071214370155300_bib3) 2010
Kingma (2024071214370155300_bib17)
Accorsi (2024071214370155300_bib68) 2022; 50
Vinyals (2024071214370155300_bib65) 2015
Boyd (2024071214370155300_bib1) 2004
Lindauer (2024071214370155300_bib9) 2022; 23
Shu (2024071214370155300_bib22) 2019
Kerschke (2024071214370155300_bib15) 2019; 27
Hutter (2024071214370155300_bib29) 2014; 206
Rice (2024071214370155300_bib11) 1976; 15
Kotthoff (2024071214370155300_bib28) 2014; 35
Leyton-Brown (2024071214370155300_bib27) 2009; 56
Hutter (2024071214370155300_bib56) 2011
Elsken (2024071214370155300_bib23) 2019; 20
Adenso-Díaz (2024071214370155300_bib53) 2006; 54
Andrychowicz (2024071214370155300_bib6) 2016
Lindauer (2024071214370155300_bib79) 2017; 244
Coy (2024071214370155300_bib52) 2001; 7
Shukla (2024071214370155300_bib37) 2013; 51
Gupta (2024071214370155300_bib81) 2017; 46
Sigurdson (2024071214370155300_bib49) 2021
Zhou (2024071214370155300_bib4) 2019
Garrido (2024071214370155300_bib36) 2010; 16
Ansótegui (2024071214370155300_bib51) 2009
Kanda (2024071214370155300_bib41) 2016; 205
Bottou (2024071214370155300_bib2) 2012
Feng (2024071214370155300_bib89) 2022; 23
Smith-Miles (2024071214370155300_bib30) 2009; 41
Neira (2024071214370155300_bib42) 2020; 158
Liu (2024071214370155300_bib57) 2020
Kadioglu (2024071214370155300_bib73) 2010
Tang (2024071214370155300_bib86) 2021; 25
Jacobs (2024071214370155300_bib5) 1988; 1
Kleinberg (2024071214370155300_bib58) 2017
Liu (2024071214370155300_bib74) 2019
Soares (2024071214370155300_bib32) 2004; 54
Hart (2024071214370155300_bib19) 1968; 4
Weisz (2024071214370155300_bib60) 2019
Johnson (2024071214370155300_bib7) 2000; 35
Misir (2024071214370155300_bib40) 2022
Liu (2024071214370155300_bib62) 2021; 66
Xu (2024071214370155300_bib72) 2010
Guerriero (2024071214370155300_bib43) 2023; 27
Alissa (2024071214370155300_bib48) 2019
Liu (2024071214370155300_bib85) 2022; 52
References_xml – volume-title: Evolutionary Multi-Task Optimization: Foundations and Methodologies
  year: 2023
  ident: 2024071214370155300_bib25
  doi: 10.1007/978-981-19-5650-8
– volume: 41
  start-page: 6
  year: 2009
  ident: 2024071214370155300_bib30
  article-title: Cross-disciplinary perspectives on meta-learning for algorithm selection
  publication-title: ACM Comput Surv
  doi: 10.1145/1456650.1456656
– volume: 279
  start-page: 94
  year: 2014
  ident: 2024071214370155300_bib75
  article-title: Population-based algorithm portfolios with automated constituent algorithms selection
  publication-title: Inf Sci
  doi: 10.1016/j.ins.2014.03.105
– volume: 26
  start-page: 490
  year: 2022
  ident: 2024071214370155300_bib44
  article-title: Black-box optimization revisited: improving algorithm selection wizards through massive benchmarking
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/TEVC.2021.3108185
– start-page: 108
  volume-title: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
  year: 2021
  ident: 2024071214370155300_bib49
  article-title: Deep learning for real-time heuristic search algorithm selection
  doi: 10.1609/aiide.v13i1.12927
– volume: 27
  start-page: 1794
  year: 2023
  ident: 2024071214370155300_bib69
  article-title: Learning-aided evolution for optimization
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/TEVC.2022.3232776
– volume-title: Handbook of Metaheuristics
  year: 2010
  ident: 2024071214370155300_bib3
  doi: 10.1007/978-1-4419-1665-5
– volume: 9
  start-page: 159
  year: 2001
  ident: 2024071214370155300_bib24
  article-title: Completely derandomized self-adaptation in evolution strategies
  publication-title: Evol Comput
  doi: 10.1162/106365601750190398
– start-page: 210
  volume-title: Proceedings of the 24th AAAI Conference on Artificial Intelligence
  year: 2010
  ident: 2024071214370155300_bib72
  article-title: Hydra: automatically configuring algorithms for portfolio-based selection
  doi: 10.1609/aaai.v24i1.7565
– volume: 290
  start-page: 405
  year: 2021
  ident: 2024071214370155300_bib13
  article-title: Machine learning for combinatorial optimization: a methodological tour d’horizon
  publication-title: Eur J Oper Res
  doi: 10.1016/j.ejor.2020.07.063
– volume: 205
  start-page: 393
  year: 2016
  ident: 2024071214370155300_bib41
  article-title: Meta-learning to select the best meta-heuristic for the traveling salesman problem: a comparison of meta-features
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.04.027
– volume: 158
  start-page: 113613
  year: 2020
  ident: 2024071214370155300_bib42
  article-title: Anytime automatic algorithm selection for knapsack
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2020.113613
– start-page: 47
  volume-title: 2014 IEEE 26th International Conference on Tools with Artificial Intelligence
  year: 2014
  ident: 2024071214370155300_bib46
  article-title: Application of machine learning to algorithm selection for TSP
  doi: 10.1109/ICTAI.2014.18
– volume: 23
  start-page: 952
  year: 2022
  ident: 2024071214370155300_bib89
  article-title: Towards faster vehicle routing by transferring knowledge from customer representation
  publication-title: IEEE Trans Intell Transp Syst
  doi: 10.1109/TITS.2020.3018903
– volume: 3
  start-page: 43
  year: 2016
  ident: 2024071214370155300_bib55
  article-title: The irace package: iterated racing for automatic algorithm configuration
  publication-title: Oper Res Perspect
  doi: 10.1016/j.orp.2016.09.002
– volume: 35
  start-page: 48
  year: 2014
  ident: 2024071214370155300_bib28
  article-title: Algorithm selection for combinatorial search problems: a survey
  publication-title: AI Mag
  doi: 10.1609/aimag.v35i3.2460
– volume: 53
  start-page: 280
  year: 2023
  ident: 2024071214370155300_bib77
  article-title: Approximately optimal construction of parallel algorithm portfolios by evolutionary intelligence (in Chinese)
  publication-title: Sci Sin Technol
  doi: 10.1360/SST-2021-0372
– volume: 26
  start-page: 597
  year: 2018
  ident: 2024071214370155300_bib34
  article-title: Leveraging TSP solver complementarity through machine learning
  publication-title: Evol Comput
  doi: 10.1162/evco_a_00215
– volume: 275
  start-page: 51
  year: 1997
  ident: 2024071214370155300_bib71
  article-title: An economics approach to hard computational problems
  publication-title: Science
  doi: 10.1126/science.275.5296.51
– volume: 27
  start-page: 3
  year: 2019
  ident: 2024071214370155300_bib15
  article-title: Automated algorithm selection: survey and perspectives
  publication-title: Evol Comput
  doi: 10.1162/evco_a_00242
– volume: 4
  start-page: 100
  year: 1968
  ident: 2024071214370155300_bib19
  article-title: A formal basis for the heuristic determination of minimum cost paths
  publication-title: IEEE Trans Syst Sci Cybern
  doi: 10.1109/TSSC.1968.300136
– volume: 66
  start-page: 100927
  year: 2021
  ident: 2024071214370155300_bib62
  article-title: Memetic search for vehicle routing with simultaneous pickup-delivery and time windows
  publication-title: Swarm Evol Comput
  doi: 10.1016/j.swevo.2021.100927
– start-page: 421
  volume-title: Neural Networks: Tricks of the Trade
  year: 2012
  ident: 2024071214370155300_bib2
  article-title: Stochastic gradient descent tricks
  doi: 10.1007/978-3-642-35289-8_25
– volume: 23
  start-page: 189
  year: 2022
  ident: 2024071214370155300_bib14
  article-title: Learning to optimize: a primer and a benchmark
  publication-title: J Mach Learn Res
  doi: 10.48550/arXiv.2103.12828
– start-page: 743
  volume-title: Proceedings of the 17th International Conference on Machine Learning
  year: 2000
  ident: 2024071214370155300_bib31
  article-title: Meta-learning by landmarking various learning algorithms
– volume: 16
  start-page: 795
  year: 2010
  ident: 2024071214370155300_bib36
  article-title: DVRP: a hard dynamic combinatorial optimisation problem tackled by an evolutionary hyper-heuristic
  publication-title: J Heuristics
  doi: 10.1007/s10732-010-9126-2
– start-page: 2023
  volume-title: Proceedings of the 26th International Joint Conference on Artificial Intelligence
  year: 2017
  ident: 2024071214370155300_bib58
  article-title: Efficiency through procrastination: approximately optimal algorithm configuration with runtime guarantees
  doi: 10.24963/ijcai.2017/281
– start-page: 8852
  volume-title: Proceedings of the 37th AAAI Conference on Artificial Intelligence
  year: 2023
  ident: 2024071214370155300_bib76
  article-title: Reliable robustness evaluation via automatically constructed attack ensembles
  doi: 10.1609/aaai.v37i7.26064
– volume: 63
  start-page: 102
  year: 2015
  ident: 2024071214370155300_bib84
  article-title: Generating new test instances by evolving in instance space
  publication-title: Comput Oper Res
  doi: 10.1016/j.cor.2015.04.022
– volume-title: Evolutionary Learning: Advances in Theories and Algorithms
  year: 2019
  ident: 2024071214370155300_bib4
  doi: 10.1007/978-981-13-5956-9
– start-page: 507
  volume-title: Learning and Intelligent Optimization
  year: 2011
  ident: 2024071214370155300_bib56
  article-title: Sequential model-based optimization for general algorithm configuration
  doi: 10.1007/978-3-642-25566-3_40
– volume: 51
  start-page: 118
  year: 2013
  ident: 2024071214370155300_bib37
  article-title: Genetic-algorithms-based algorithm portfolio for inventory routing problem with stochastic demand
  publication-title: Int J Prod Res
  doi: 10.1080/00207543.2011.653010
– volume: 27
  start-page: 12997
  year: 2023
  ident: 2024071214370155300_bib43
  article-title: A hierarchical hyper-heuristic for the bin packing problem
  publication-title: Soft Comput
  doi: 10.1007/s00500-022-07118-4
– volume: 206
  start-page: 79
  year: 2014
  ident: 2024071214370155300_bib29
  article-title: Algorithm runtime prediction: methods & evaluation
  publication-title: Artif Intell
  doi: 10.1016/j.artint.2013.10.003
– start-page: 253
  volume-title: Proceedings of the Genetic and Evolutionary Computation Conference
  year: 2018
  ident: 2024071214370155300_bib39
  article-title: Algorithm selection on generalized quadratic assignment problem landscapes
  doi: 10.1145/3205455.3205585
– start-page: 751
  volume-title: Frontiers in Artificial Intelligence and Applications
  year: 2010
  ident: 2024071214370155300_bib73
  article-title: ISAC – instance-specific algorithm configuration
– start-page: 3988
  volume-title: Proceedings of the 30th International Conference on Neural Information Processing Systems
  year: 2016
  ident: 2024071214370155300_bib6
  article-title: Learning to learn by gradient descent by gradient descent
  doi: 10.48550/arXiv.1606.04474
– volume: 232
  start-page: 20
  year: 2016
  ident: 2024071214370155300_bib12
  article-title: SATenstein: automatically building local search SAT solvers from components
  publication-title: Artif Intell
  doi: 10.1016/j.artint.2015.11.002
– volume: 54
  start-page: 195
  year: 2004
  ident: 2024071214370155300_bib32
  article-title: A meta-learning method to select the kernel width in support vector regression
  publication-title: Mach Learn
  doi: 10.1023/B:MACH.0000015879.28004.9b
– volume-title: Foundations of Genetic Programming
  year: 2002
  ident: 2024071214370155300_bib18
  doi: 10.1007/978-3-662-04726-2
– start-page: 18
  volume-title: 2021 International Joint Conference on Neural Networks (IJCNN)
  year: 2021
  ident: 2024071214370155300_bib35
  article-title: Towards feature-free TSP solver selection: a deep learning approach
  doi: 10.1109/IJCNN52387.2021.9533538
– start-page: 5522
  volume-title: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  year: 2022
  ident: 2024071214370155300_bib87
  article-title: Learning to solve hard minimal problems
  doi: 10.1109/CVPR52688.2022.00545
– start-page: 142
  volume-title: Principles and Practice of Constraint Programming
  year: 2009
  ident: 2024071214370155300_bib51
  article-title: A gender-based genetic algorithm for the automatic configuration of algorithms
  doi: 10.1007/978-3-642-04244-7_14
– start-page: 24
  volume-title: 5th International Conference on Learning Representations
  year: 2017
  ident: 2024071214370155300_bib64
  article-title: Neural combinatorial optimization with reinforcement learning
– start-page: 3364
  volume-title: Proceedings of the AAAI Conference on Artificial Intelligence
  year: 2015
  ident: 2024071214370155300_bib78
  article-title: Automatic configuration of sequential planning portfolios
  doi: 10.1609/aaai.v29i1.9640
– volume: 24
  start-page: 423
  year: 1997
  ident: 2024071214370155300_bib33
  article-title: Combining and selecting forecasting models using rule based induction
  publication-title: Comput Oper Res
  doi: 10.1016/S0305-0548(96)00062-7
– start-page: 186
  volume-title: Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems
  year: 2010
  ident: 2024071214370155300_bib61
  article-title: Automated configuration of mixed integer programming solvers
  doi: 10.1007/978-3-642-13520-0_23
– volume: 267
  start-page: 66
  year: 1992
  ident: 2024071214370155300_bib20
  article-title: Genetic algorithms
  publication-title: Sci Am
  doi: 10.1038/scientificamerican0792-66
– start-page: 198
  volume-title: Proceedings of the Genetic and Evolutionary Computation Conference
  year: 2019
  ident: 2024071214370155300_bib48
  article-title: Algorithm selection using deep learning without feature extraction
  doi: 10.1145/3321707.3321845
– volume: 35
  start-page: 205
  year: 2000
  ident: 2024071214370155300_bib7
  article-title: Reinforcement learning: an introduction
  publication-title: Neurocomputing
  doi: 10.1016/S0925-2312(00)00324-6
– volume: 25
  start-page: 595
  year: 2021
  ident: 2024071214370155300_bib86
  article-title: Few-shots parallel algorithm portfolio construction via co-evolution
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/TEVC.2021.3059661
– volume: 550
  start-page: 354
  year: 2017
  ident: 2024071214370155300_bib63
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
  doi: 10.1038/nature24270
– volume: 244
  start-page: 272
  year: 2017
  ident: 2024071214370155300_bib79
  article-title: Automatic construction of parallel portfolios via algorithm configuration
  publication-title: Artif Intell
  doi: 10.1016/j.artint.2016.05.004
– start-page: 495
  volume-title: Proceedings of the Companion Conference on Genetic and Evolutionary Computation
  year: 2023
  ident: 2024071214370155300_bib45
  article-title: Comparing algorithm selection approaches on black-box optimization problems
  doi: 10.1145/3583133.3590697
– start-page: 2384
  volume-title: Proceedings of the AAAI Conference on Artificial Intelligence
  year: 2020
  ident: 2024071214370155300_bib57
  article-title: On performance estimation in automatic algorithm configuration
  doi: 10.1609/aaai.v34i03.5618
– volume: 36
  start-page: 267
  year: 2009
  ident: 2024071214370155300_bib8
  article-title: Paramils: an automatic algorithm configuration framework
  publication-title: J Artif Intell Res
  doi: 10.1613/jair.2861
– start-page: 1471
  volume-title: Proceedings of the Genetic and Evolutionary Computation Conference Companion
  year: 2017
  ident: 2024071214370155300_bib38
  article-title: Instance-based algorithm selection on quadratic assignment problem landscapes
  doi: 10.1145/3067695.3082513
– volume: 54
  start-page: 175
  year: 2022
  ident: 2024071214370155300_bib10
  article-title: Automl to date and beyond: challenges and opportunities
  publication-title: ACM Comput Surv
  doi: 10.1145/3470918
– start-page: 5257
  volume-title: Proceedings of the 35th International Conference on Machine Learning
  year: 2018
  ident: 2024071214370155300_bib59
  article-title: LeapsAndBounds: a method for approximately optimal algorithm configuration
– start-page: 1919
  volume-title: Proceedings of the 33rd International Conference on Neural Information Processing Systems
  year: 2019
  ident: 2024071214370155300_bib22
  article-title: Meta-weight-net: learning an explicit mapping for sample weighting
– volume: 15
  start-page: 65
  year: 1976
  ident: 2024071214370155300_bib11
  article-title: The algorithm selection problem
  publication-title: Adv Comput
  doi: 10.1016/S0065-2458(08)60520-3
– start-page: 213
  volume-title: Proceedings of the 2017 Conference on Learning Theory
  year: 2017
  ident: 2024071214370155300_bib83
  article-title: Learning-theoretic foundations of algorithm configuration for combinatorial partitioning problems
– volume: 46
  start-page: 992
  year: 2017
  ident: 2024071214370155300_bib81
  article-title: A PAC approach to application-specific algorithm selection
  publication-title: SIAM J Comput
  doi: 10.1137/15M1050276
– volume: 20
  start-page: 55
  year: 2019
  ident: 2024071214370155300_bib23
  article-title: Neural architecture search: a survey
  publication-title: J Mach Learn Res
– start-page: 11
  volume-title: Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation
  year: 2002
  ident: 2024071214370155300_bib54
  article-title: A racing algorithm for configuring metaheuristics
– start-page: 6707
  volume-title: Proceedings of the 36th International Conference on Machine Learning
  year: 2019
  ident: 2024071214370155300_bib60
  article-title: CapsAndRuns: an improved method for approximately optimal algorithm configuration
– volume: 52
  start-page: 784
  year: 2022
  ident: 2024071214370155300_bib85
  article-title: Generative adversarial construction of parallel portfolios
  publication-title: IEEE Trans Cybern
  doi: 10.1109/TCYB.2020.2984546
– volume: 23
  start-page: 54
  year: 2022
  ident: 2024071214370155300_bib9
  article-title: SMAC3: a versatile Bayesian optimization package for hyperparameter optimization
  publication-title: J Mach Learn Res
  doi: 10.48550/arXiv.2109.09831
– volume: 56
  start-page: 22
  year: 2009
  ident: 2024071214370155300_bib27
  article-title: Empirical hardness models: methodology and a case study on combinatorial auctions
  publication-title: J ACM
  doi: 10.1145/1538902.1538906
– volume: 75
  start-page: 425
  year: 2022
  ident: 2024071214370155300_bib16
  article-title: A survey of methods for automated algorithm configuration
  publication-title: J Artif Intell Res
  doi: 10.1613/jair.1.13676
– volume: 18
  start-page: 14
  year: 2023
  ident: 2024071214370155300_bib67
  article-title: How good is neural combinatorial optimization? A systematic evaluation on the traveling salesman problem
  publication-title: IEEE Comput Intell Mag
  doi: 10.1109/MCI.2023.3277768
– start-page: 919
  volume-title: Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing
  year: 2021
  ident: 2024071214370155300_bib82
  article-title: How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design
  doi: 10.1145/3406325.3451036
– volume: 7
  start-page: 77
  year: 2001
  ident: 2024071214370155300_bib52
  article-title: Using experimental design to find effective parameter settings for heuristics
  publication-title: J Heuristics
  doi: 10.1023/A:1026569813391
– start-page: 1560
  volume-title: Proceedings of the 33rd AAAI Conference on Artificial Intelligence
  year: 2019
  ident: 2024071214370155300_bib74
  article-title: Automatic construction of parallel portfolios via explicit instance grouping
  doi: 10.1609/aaai.v33i01.33011560
– volume: 1
  start-page: 295
  year: 1988
  ident: 2024071214370155300_bib5
  article-title: Increased rates of convergence through learning rate adaptation
  publication-title: Neural Netw
  doi: 10.1016/0893-6080(88)90003-2
– start-page: 6281
  volume-title: Proceedings of the 33rd International Conference on Neural Information Processing Systems
  year: 2019
  ident: 2024071214370155300_bib66
  article-title: Learning to perform local rewriting for combinatorial optimization
– volume: 50
  start-page: 229
  year: 2022
  ident: 2024071214370155300_bib68
  article-title: Guidelines for the computational testing of machine learning approaches to vehicle routing problems
  publication-title: Oper Res Lett
  doi: 10.1016/j.orl.2022.01.018
– year: 2023
  ident: 2024071214370155300_bib70
  article-title: Knowledge learning for evolutionary computation
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/TEVC.2023.3278132
– volume: 44
  start-page: 5149
  year: 2022
  ident: 2024071214370155300_bib21
  article-title: Meta-learning in neural networks: a survey
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2021.3079209
– start-page: 235
  volume-title: Proceedings of the 10th National Conference on Aritificial Intelligence
  year: 1992
  ident: 2024071214370155300_bib50
  article-title: COMPOSER: a probabilistic solution to the utility problem in speed-up learning
– volume: 54
  start-page: 99
  year: 2006
  ident: 2024071214370155300_bib53
  article-title: Fine-tuning of algorithms using fractional experimental designs and local search
  publication-title: Oper Res
  doi: 10.1287/opre.1050.0243
– start-page: 1280
  volume-title: Proceedings of the 30th AAAI Conference on Artificial Intelligence
  year: 2016
  ident: 2024071214370155300_bib47
  article-title: Deep learning for algorithm portfolios
  doi: 10.1609/aaai.v30i1.10170
– volume-title: Convex Optimization
  year: 2004
  ident: 2024071214370155300_bib1
  doi: 10.1017/CBO9780511804441
– volume: 1
  start-page: 67
  year: 1997
  ident: 2024071214370155300_bib26
  article-title: No free lunch theorems for optimization
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/4235.585893
– volume-title: Proceedings of the 28th International Conference on Neural Information Processing Systems
  year: 2015
  ident: 2024071214370155300_bib65
  article-title: Pointer networks
– volume: 594
  start-page: 207
  year: 2021
  ident: 2024071214370155300_bib88
  article-title: A graph placement methodology for fast chip design
  publication-title: Nature
  doi: 10.1038/s41586-021-03544-w
– start-page: 22
  volume-title: 2022 IEEE Symposium Series on Computational Intelligence (SSCI)
  year: 2022
  ident: 2024071214370155300_bib40
  article-title: Cross-domain algorithm selection: algorithm selection across selection hyper-heuristics
  doi: 10.1109/SSCI51031.2022.10022078
– volume-title: 3rd International Conference on Learning Representations
  ident: 2024071214370155300_bib17
  article-title: Adam: a method for stochastic optimization
– start-page: 8883
  volume-title: Proceedings of the 33rd International Conference on Neural Information Processing Systems
  year: 2019
  ident: 2024071214370155300_bib80
  article-title: Procrastinating with confidence: near-optimal, anytime, adaptive algorithm configuration
SSID ssib051367741
ssib050735980
ssj0001257732
Score 2.3971367
SecondaryResourceType review_article
Snippet Most optimization problems of practical significance are typically solved by highly configurable parameterized algorithms. To achieve the best performance on a...
SourceID proquest
pubmed
crossref
oup
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage nwae132
Title Learn to optimize—a brief overview
URI https://www.ncbi.nlm.nih.gov/pubmed/39007005
https://www.proquest.com/docview/3080635679
Volume 11
WOSCitedRecordID wos001221382600001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2053-714X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001257732
  issn: 2095-5138
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2053-714X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib050735980
  issn: 2095-5138
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVASL
  databaseName: Oxford Journals Open Access Collection
  customDbUrl:
  eissn: 2053-714X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001257732
  issn: 2095-5138
  databaseCode: TOX
  dateStart: 20140301
  isFulltext: true
  titleUrlDefault: https://academic.oup.com/journals/
  providerName: Oxford University Press
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3LSsQwFA06uHDjA1_jY6wwKyFMmzRNshSZwY2jixG6K02awoC2Mu0ouBA_wi_0S7zpQxgd1E03vYTm5iQ5tzc5F6G-5sTExo9xIIWPgf8zLIj2MAsAzFQZq6lVFZvg47EIQ3nbHJAtlqTwJR1kxWyQPccG4iZYaj0mLJwnN2ELG2A0VobuC3bMqpC1BWXqXy2M86pUGQFCgeG9aG7qfWt-YW9auO_2g3ZW289o878fvoU2GoLpXNSI2EYrJttB_UpG1SlzJ4cl4mH6Yj7e3mNHQZycOvYQp00Q7KK70XByeYWb-ghYU8ZL7DPPiMAPtE4MxCGKeKkMFLiepIaz2E00xJ-eIq7WNKBEMe1rN4VZ6nIFhoruoU6WZ-YAOTCOKTPUSO7FfkqUSoEG8oRJkviSStpF561nIt2Ih9saFvdRncSmEXQ2ajrbBQi0xo-1ZsZys1Nw8e8WZ637I0C9TWXEmcnnRUSB6FplPS67aL8el6-GqLQaRi47_LP9I7ROgKPU5_mOUaeczc0JWtNP5bSY9dAqD0WvCtLhef067FWw-wQGts5f
linkProvider Oxford University Press
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=Learn+to+optimize-a+brief+overview&rft.jtitle=National+science+review&rft.au=Tang%2C+Ke&rft.au=Yao%2C+Xin&rft.date=2024-08-01&rft.issn=2053-714X&rft.eissn=2053-714X&rft.volume=11&rft.issue=8&rft.spage=nwae132&rft_id=info:doi/10.1093%2Fnsr%2Fnwae132&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2095-5138&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2095-5138&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2095-5138&client=summon