Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers

Automated hyperparameter optimization (HPO) has gained great popularity and is an important component of most automated machine learning frameworks. However, the process of designing HPO algorithms is still an unsystematic and manual process: New algorithms are often built on top of prior work, wher...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on evolutionary computation Ročník 26; číslo 6; s. 1
Hlavní autori:	Moosbauer, Julia, Binder, Martin, Schneider, Lennart, Pfisterer, Florian, Becker, Marc, Lang, Michel, Kotthoff, Lars, Bischl, Bernd
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Ablation algorithm analysis Algorithm design Algorithms Approximation algorithms automated machine learning Automation Bayes methods Benchmarks Configurations Design optimization hyperparameter optimization Machine learning Machine learning algorithms Mathematical models multifidelity Optimization Prediction algorithms Software algorithms
ISSN:	1089-778X, 1941-0026
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Automated hyperparameter optimization (HPO) has gained great popularity and is an important component of most automated machine learning frameworks. However, the process of designing HPO algorithms is still an unsystematic and manual process: New algorithms are often built on top of prior work, where limitations are identified and improvements are proposed. Even though this approach is guided by expert knowledge, it is still somewhat arbitrary. The process rarely allows for gaining a holistic understanding of which algorithmic components drive performance and carries the risk of overlooking good algorithmic design choices. We present a principled approach to automated benchmark-driven algorithm design applied to multi-fidelity HPO (MF-HPO). First, we formalize a rich space of MF-HPO candidates that includes, but is not limited to, common existing HPO algorithms and then present a configurable framework covering this space. To find the best candidate automatically and systematically, we follow a programming-by-optimization approach and search over the space of algorithm candidates via Bayesian optimization. We challenge whether the found design choices are necessary or could be replaced by more naive and simpler ones by performing an ablation analysis. We observe that using a relatively simple configuration (in some ways, simpler than established methods) performs very well as long as some critical configuration parameters are set to the right value.
AbstractList	Automated hyperparameter optimization (HPO) has gained great popularity and is an important component of most automated machine learning frameworks. However, the process of designing HPO algorithms is still an unsystematic and manual process: New algorithms are often built on top of prior work, where limitations are identified and improvements are proposed. Even though this approach is guided by expert knowledge, it is still somewhat arbitrary. The process rarely allows for gaining a holistic understanding of which algorithmic components drive performance and carries the risk of overlooking good algorithmic design choices. We present a principled approach to automated benchmark-driven algorithm design applied to multi-fidelity HPO (MF-HPO). First, we formalize a rich space of MF-HPO candidates that includes, but is not limited to, common existing HPO algorithms and then present a configurable framework covering this space. To find the best candidate automatically and systematically, we follow a programming-by-optimization approach and search over the space of algorithm candidates via Bayesian optimization. We challenge whether the found design choices are necessary or could be replaced by more naive and simpler ones by performing an ablation analysis. We observe that using a relatively simple configuration (in some ways, simpler than established methods) performs very well as long as some critical configuration parameters are set to the right value. Automated hyperparameter optimization (HPO) has gained great popularity and is an important component of most automated machine learning frameworks. However, the process of designing HPO algorithms is still an unsystematic and manual process: new algorithms are often built on top of prior work, where limitations are identified and improvements are proposed. Even though this approach is guided by expert knowledge, it is still somewhat arbitrary. The process rarely allows for gaining a holistic understanding of which algorithmic components drive performance and carries the risk of overlooking good algorithmic design choices. We present a principled approach to automated benchmark-driven algorithm design applied to multifidelity HPO (MF-HPO). First, we formalize a rich space of MF-HPO candidates that includes, but is not limited to, common existing HPO algorithms and then present a configurable framework covering this space. To find the best candidate automatically and systematically, we follow a programming-by-optimization approach and search over the space of algorithm candidates via Bayesian optimization. We challenge whether the found design choices are necessary or could be replaced by more naive and simpler ones by performing an ablation analysis. We observe that using a relatively simple configuration (in some ways, simpler than established methods) performs very well as long as some critical configuration parameters are set to the right value.
Author	Becker, Marc Pfisterer, Florian Bischl, Bernd Moosbauer, Julia Lang, Michel Schneider, Lennart Kotthoff, Lars Binder, Martin
Author_xml	– sequence: 1 givenname: Julia orcidid: 0000-0002-0000-9297 surname: Moosbauer fullname: Moosbauer, Julia – sequence: 2 givenname: Martin surname: Binder fullname: Binder, Martin – sequence: 3 givenname: Lennart orcidid: 0000-0003-4152-5308 surname: Schneider fullname: Schneider, Lennart – sequence: 4 givenname: Florian orcidid: 0000-0001-8867-762X surname: Pfisterer fullname: Pfisterer, Florian – sequence: 5 givenname: Marc surname: Becker fullname: Becker, Marc – sequence: 6 givenname: Michel surname: Lang fullname: Lang, Michel – sequence: 7 givenname: Lars orcidid: 0000-0003-4635-6873 surname: Kotthoff fullname: Kotthoff, Lars – sequence: 8 givenname: Bernd orcidid: 0000-0001-6002-6980 surname: Bischl fullname: Bischl, Bernd
BookMark	eNp9kE9PAjEQxRuDiYh-AONlE8-L_bd0e0RAMSFyQeNt022nWoTu2i1G_PQuQjx48DSTzPvNzHunqOMrDwhdENwnBMvrxeRp1KeY0j6jhDA2OEJdIjlJMaaDTtvjXKZC5M8n6LRplhgTnhHZRQ_DTazWKoJJbsDr17UKb-k4uA_wyRga9-IT5U0y-axXyqvoKp9UNpluawi1CmoNEUIyr6Nbuy8IzRk6tmrVwPmh9tDj7WQxmqaz-d39aDhLdftaTFkOmtoys6wkZUasMrLE1GYqlxrwINOaC4ZzzYhmXJnMGmM516URwITKDOuhq_3eOlTvG2hisaw2wbcnCyo4FZiJjLcqslfpUDVNAFvUwbUOtwXBxS62YhdbsYutOMTWMuIPo138MR6Dcqt_ycs96QDg95KU7ZBT9g2qCn3R
CODEN	ITEVF5
CitedBy_id	crossref_primary_10_1002_widm_1484 crossref_primary_10_1016_j_jclepro_2025_145710
Cites_doi	10.1214/aoms/1177730196 10.1109/4235.585893 10.1007/s11721-012-0070-7 10.1007/978-3-642-34413-8_5 10.1109/TEVC.2015.2474158 10.1111/0272-4332.00040 10.1007/978-0-387-88843-9_3 10.1023/A:1008306431147 10.1007/s10732-014-9275-9 10.1613/jair.2861 10.1023/A:1012771025575 10.1145/3097983.3098043 10.1145/3437984.3458834 10.1016/j.orp.2016.09.002 10.1023/A:1010933404324 10.1007/978-3-642-44973-4_7 10.1007/978-3-030-05318-5_4 10.1007/978-3-642-02538-9_13 10.1109/TEVC.2011.2182651 10.1145/2076450.2076469 10.1007/BF00143877 10.1145/3071178.3071238 10.1214/12-AOS1049 10.1007/978-3-642-25566-3_40 10.1007/978-3-642-00483-4 10.1109/SSCI.2016.7850138 10.1145/3449726.3463167 10.1016/j.ejor.2017.01.035 10.1017/S0269888901000029 10.1109/WICSA.2011.37 10.1023/A:1006556606079
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TEVC.2022.3211336
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications 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 Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1941-0026
EndPage	1
ExternalDocumentID	10_1109_TEVC_2022_3211336 9913342
Genre	orig-research
GrantInformation_xml	– fundername: Bayerische Staatsministerium f?r Wirtschaft, Landesentwicklung und Energie grantid: 20-3410-2-9-8 funderid: 10.13039/501100020639 – fundername: National Science Foundation (NSF) grantid: 1813537 – fundername: Research Center Trustworthy Data Science and Security
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IF 6IK 97E AAJGR AASAJ AAWTH ABJNI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD ESBDL HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c336t-38ec2fb5f3b1b51fad9b02f5a89ce065cc47308c31c34ad5fddf44cbd7e37a5d3
IEDL.DBID	RIE
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000892933300013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1089-778X
IngestDate	Sun Nov 30 04:10:46 EST 2025 Sat Nov 29 03:13:49 EST 2025 Tue Nov 18 21:13:14 EST 2025 Tue Nov 25 14:44:26 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c336t-38ec2fb5f3b1b51fad9b02f5a89ce065cc47308c31c34ad5fddf44cbd7e37a5d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6002-6980 0000-0003-4152-5308 0000-0002-0000-9297 0000-0001-8867-762X 0000-0003-4635-6873
OpenAccessLink	https://ieeexplore.ieee.org/document/9913342
PQID	2742703754
PQPubID	85418
PageCount	1
ParticipantIDs	crossref_primary_10_1109_TEVC_2022_3211336 ieee_primary_9913342 proquest_journals_2742703754 crossref_citationtrail_10_1109_TEVC_2022_3211336
PublicationCentury	2000
PublicationDate	2022-12-01
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: 2022-12-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on evolutionary computation
PublicationTitleAbbrev	TEVC
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 lindauer (ref36) 2021 ref53 ref52 ref54 ref10 lindauer (ref35) 2019 ref51 jamieson (ref19) 2016; 51 ref45 ref42 ref41 khudabukhsh (ref24) 2009 ref43 ref49 bischl (ref1) 2021 li (ref15) 2020 snoek (ref8) 2012 ref4 ref3 hutter (ref39) 2014; 32 ref5 bergstra (ref47) 2011; 24 ref40 turner (ref9) 2020; 133 ref37 ref31 ref30 ref33 ref32 bischl (ref11) 2014 ref2 ref38 malkomes (ref34) 2018; 31 gonzález (ref12) 2016; 51 pfisterer (ref50) 2021 falkner (ref16) 2018; 80 karnin (ref46) 2013 bergstra (ref7) 2012; 13 ref23 ref26 ref25 ref20 ref22 ref21 sculley (ref18) 2015 li (ref14) 2017; 18 ref28 ref27 ref29 demšar (ref55) 2006; 7 swersky (ref6) 2014 klein (ref44) 2020 tiao (ref17) 2020 klein (ref48) 2017
References_xml	– volume: 24 start-page: 2546 year: 2011 ident: ref47 article-title: Algorithms for hyper-parameter optimization publication-title: Proc Int Conf Adv Neural Inf Process Syst – ident: ref38 doi: 10.1214/aoms/1177730196 – volume: 51 start-page: 648 year: 2016 ident: ref12 article-title: Batch Bayesian optimization via local penalization publication-title: Proc 19th Int Conf Artif Intell Stat (AISTATS) – ident: ref3 doi: 10.1109/4235.585893 – ident: ref42 doi: 10.1007/s11721-012-0070-7 – ident: ref10 doi: 10.1007/978-3-642-34413-8_5 – ident: ref27 doi: 10.1109/TEVC.2015.2474158 – ident: ref37 doi: 10.1111/0272-4332.00040 – ident: ref25 doi: 10.1007/978-0-387-88843-9_3 – ident: ref4 doi: 10.1023/A:1008306431147 – start-page: 528 year: 2017 ident: ref48 article-title: Fast Bayesian optimization of machine learning hyperparameters on large datasets publication-title: Proc Int Conf Artif Intell Stat – ident: ref40 doi: 10.1007/s10732-014-9275-9 – ident: ref31 doi: 10.1613/jair.2861 – ident: ref51 doi: 10.1023/A:1012771025575 – volume: 80 start-page: 1436 year: 2018 ident: ref16 article-title: BOHB: Robust and efficient hyperparameter optimization at scale publication-title: Proc 35th Int Conf Mach Learn (ICML) – ident: ref49 doi: 10.1145/3097983.3098043 – ident: ref41 doi: 10.1145/3437984.3458834 – year: 2021 ident: ref36 article-title: SMAC3: A versatile Bayesian optimization package for hyperparameter optimization publication-title: arXiv 2109 09831 – year: 2020 ident: ref44 article-title: Model-based asynchronous hyperparameter and neural architecture search publication-title: arXiv 2003 10865 – volume: 32 start-page: 754 year: 2014 ident: ref39 article-title: An efficient approach for assessing hyperparameter importance publication-title: Proc 31st Int Conf Mach Learn – start-page: 517 year: 2009 ident: ref24 article-title: SATenstein: Automatically building local search SAT solvers from components publication-title: Proc 21st Int Joint Conf Artif Intell – volume: 13 start-page: 281 year: 2012 ident: ref7 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – start-page: 1238 year: 2013 ident: ref46 article-title: Almost optimal exploration in multi-armed bandits publication-title: Proc Int Conf Mach Learn – year: 2020 ident: ref17 article-title: Model-based asynchronous hyperparameter optimization publication-title: arXiv 2003 10865 – volume: 51 start-page: 240 year: 2016 ident: ref19 article-title: Non-stochastic best arm identification and hyperparameter optimization publication-title: Proc 19th Int Conf Artif Intell Stat (AISTATS) – volume: 31 start-page: 5984 year: 2018 ident: ref34 article-title: Automating Bayesian optimization with Bayesian optimization publication-title: Proc Int Conf Adv Neural Inf Process Syst – ident: ref29 doi: 10.1016/j.orp.2016.09.002 – ident: ref53 doi: 10.1023/A:1010933404324 – volume: 133 start-page: 3 year: 2020 ident: ref9 article-title: Bayesian optimization is superior to random search for machine learning hyperparameter tuning: Analysis of the black-box optimization challenge 2020 publication-title: Proc NeurIPS Competition Demonstration Track – ident: ref13 doi: 10.1007/978-3-642-44973-4_7 – start-page: 2503 year: 2015 ident: ref18 article-title: Hidden technical debt in machine learning systems publication-title: Proc Annu Conf Neural Inf Process Syst – ident: ref2 doi: 10.1007/978-3-030-05318-5_4 – volume: 18 start-page: 1 year: 2017 ident: ref14 article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization publication-title: J Mach Learn Res – ident: ref28 doi: 10.1007/978-3-642-02538-9_13 – ident: ref26 doi: 10.1109/TEVC.2011.2182651 – ident: ref20 doi: 10.1145/2076450.2076469 – ident: ref21 doi: 10.1007/BF00143877 – ident: ref30 doi: 10.1145/3071178.3071238 – year: 2014 ident: ref6 article-title: Freeze-thaw Bayesian optimization publication-title: arXiv 1406 3896 – ident: ref54 doi: 10.1214/12-AOS1049 – ident: ref5 doi: 10.1007/978-3-642-25566-3_40 – start-page: 2951 year: 2012 ident: ref8 article-title: Practical Bayesian optimization of machine learning algorithms publication-title: Proc 25th Int Conf Neural Inf Process Syst Vol 2 – start-page: 173 year: 2014 ident: ref11 article-title: MOI-MBO: Multiobjective infill for parallel model-based optimization publication-title: Proc 8th Int Conf Learn Intell Optim – ident: ref45 doi: 10.1007/978-3-642-00483-4 – ident: ref33 doi: 10.1109/SSCI.2016.7850138 – year: 2019 ident: ref35 article-title: Towards assessing the impact of Bayesian optimization's own hyperparameters publication-title: arXiv 1908 06674 – year: 2021 ident: ref50 article-title: YAHPO gym-Design criteria and a new multifidelity benchmark for hyperparameter optimization publication-title: arXiv 2109 03670 – ident: ref43 doi: 10.1145/3449726.3463167 – ident: ref52 doi: 10.1016/j.ejor.2017.01.035 – ident: ref22 doi: 10.1017/S0269888901000029 – ident: ref23 doi: 10.1109/WICSA.2011.37 – volume: 7 start-page: 1 year: 2006 ident: ref55 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J Mach Learn Res – start-page: 230 year: 2020 ident: ref15 article-title: A system for massively parallel hyperparameter tuning publication-title: Proc Int Conf Mach Learn Syst (MLSys) – year: 2021 ident: ref1 article-title: Hyperparameter optimization: Foundations, algorithms, best practices and open challenges publication-title: arXiv 2107 05847 – ident: ref32 doi: 10.1023/A:1006556606079
SSID	ssj0014519
Score	2.4330502
Snippet	Automated hyperparameter optimization (HPO) has gained great popularity and is an important component of most automated machine learning frameworks. However,...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Ablation algorithm analysis Algorithm design Algorithms Approximation algorithms automated machine learning Automation Bayes methods Benchmarks Configurations Design optimization hyperparameter optimization Machine learning Machine learning algorithms Mathematical models multifidelity Optimization Prediction algorithms Software algorithms
Title	Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers
URI	https://ieeexplore.ieee.org/document/9913342 https://www.proquest.com/docview/2742703754
Volume	26
WOSCitedRecordID	wos000892933300013&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0026 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014519 issn: 1089-778X databaseCode: RIE dateStart: 19970101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VigEGCi2IQkEemBBp49hpkrH0Q50KQ0HdIsd2BII2KG0Z-PWcnbQggZDYIsUXJXn2-c539w7gypOm7tfzHZ_iDOZuEjiGdc1RXKqu5gqdOWmbTQSTSTibRfcVuNnWwmitbfKZbptLG8tXmVybo7IO2jKMcVS4O0HQLWq1thEDQ5NSJNNHaDGGszKCSd2oMx0-9tET9Lw2Q3eHWTbmrz3INlX5oYnt9jKq_e_FDuGgNCNJr8D9CCp6UYfapkUDKVdsHfa_8Q02YNJbrzI0UbUit3j_aS7yF2eQG4VHBjaVg4iFIiYvTxSnhCRLyRhd1dxQhM9N6gy5QyUzf_5As_EYHkbDaX_slA0VHIlfvXJYqKWXJn7KEpr4NBUqSlwv9UUYSY22iJQcF3woGZWMC-WnSqWcy0QFmgXCV-wEqotsoU-BmKh3GAmGvrXgVHUT7VKB8jSUSklNm-BufnEsS7Zx0_TiNbZehxvFBpXYoBKXqDTheivyVlBt_DW4YWDYDiwRaEJrg2NcLsZlbKLRge31e_a71DnsmWcXWSotqK7ytb6AXfm-el7ml3aefQILO9C-
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB4hQAIOsLxEgd31gRMibRw7JDmyPFS0UDgU1Fvk2I5Au21QaDnw65lx3C7SIiRukWIrj88ez3jG3wdwEGk69xvFQcxxBMuwSAJiXQuM1ObYSoPBnHZiE0mvlw4G2e0cHM3OwlhrXfGZbdOly-WbSk9oq6yDvowQEg3uAiln-dNas5wBEaU05fQZ-ozpwOcweZh1-uf3pxgLRlFbYMAjHB_zv1XIyar8Z4vdAnOx9rVX-war3pFkJw3y6zBnRxuwNhVpYH7ObsDKO8bBTeidTMYVOqnWsF94_2Go6j_BWU0mj525Yg6mRoZRZZ5q9glZVbIuBqs1kYQPqXiG3aCZGT6-ouO4BXcX5_3TbuAlFQKNXz0ORGp1VBZxKQpexLxUJivCqIxVmmmL3ojWEqd8qgXXQioTl8aUUurCJFYkKjZiG-ZH1cjuAKO8d5opgdG1ktwcFzbkCvvzVBujLW9BOP3FufZ84yR78Td3cUeY5YRKTqjkHpUWHM66PDVkG5813iQYZg09Ai3Yn-KY--n4nFM-OnFqv7sf9_oJS93-9VV-ddn7vQfL9JymZmUf5sf1xH6HRf0yfnyuf7gx9wYTNdQH
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=Automated+Benchmark-Driven+Design+and+Explanation+of+Hyperparameter+Optimizers&rft.jtitle=IEEE+transactions+on+evolutionary+computation&rft.au=Moosbauer%2C+Julia&rft.au=Binder%2C+Martin&rft.au=Schneider%2C+Lennart&rft.au=Pfisterer%2C+Florian&rft.date=2022-12-01&rft.issn=1089-778X&rft.eissn=1941-0026&rft.volume=26&rft.issue=6&rft.spage=1336&rft.epage=1350&rft_id=info:doi/10.1109%2FTEVC.2022.3211336&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TEVC_2022_3211336
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-778X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-778X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-778X&client=summon