Hospital simulation model optimisation with a random ReLU expansion surrogate model

Laurens Bliek; Arthur Guijt; Rickard Karlsson

doi:10.1145/3449726.3463279

Hospital simulation model optimisation with a random ReLU expansion surrogate model

Laurens Bliek, Arthur Guijt, Rickard Karlsson

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

Samenvatting

The industrial challenge of the GECCO 2021 conference is an expensive optimisation problem, where the parameters of a hospital simulation model need to be tuned to optimality. We show how a surrogate-based optimisation framework, with a random ReLU expansion as the surrogate model, outperforms other methods such as Bayesian optimisation, Hyperopt, and random search on this problem.

Originele taal-2	Engels
Titel	GECCO '21
Subtitel	Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion
Uitgeverij	Association for Computing Machinery, Inc
Pagina's	13-14
Aantal pagina's	2
ISBN van elektronische versie	9781450383516
DOI's	https://doi.org/10.1145/3449726.3463279
Status	Gepubliceerd - 7 jul. 2021
Evenement	2021 Genetic and Evolutionary Computation Conference, GECCO 2021 - Virtual/Online, Lille, Frankrijk Duur: 10 jul. 2021 → 14 jul. 2021 https://gecco-2021.sigevo.org/HomePage

Congres

Congres	2021 Genetic and Evolutionary Computation Conference, GECCO 2021
Verkorte titel	GECCO 2021
Land/Regio	Frankrijk
Stad	Lille
Periode	10/07/21 → 14/07/21
Internet adres	https://gecco-2021.sigevo.org/HomePage

Bibliografische nota

Publisher Copyright:
© 2021 Owner/Author.

Duurzame ontwikkelingsdoelstellingen van de VN

Deze output draagt bij aan de volgende duurzame ontwikkelingsdoelstelling(en)

Toegang tot document

10.1145/3449726.3463279

Andere bestanden en links

Link naar publicatie in Scopus

Citeer dit

@inproceedings{0e4f500207b04c54b15f01b75aa2c216,

title = "Hospital simulation model optimisation with a random ReLU expansion surrogate model",

abstract = "The industrial challenge of the GECCO 2021 conference is an expensive optimisation problem, where the parameters of a hospital simulation model need to be tuned to optimality. We show how a surrogate-based optimisation framework, with a random ReLU expansion as the surrogate model, outperforms other methods such as Bayesian optimisation, Hyperopt, and random search on this problem. ",

keywords = "expensive optimisation, simulation optimisation, surrogate models",

author = "Laurens Bliek and Arthur Guijt and Rickard Karlsson",

note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 2021 Genetic and Evolutionary Computation Conference, GECCO 2021 ; Conference date: 10-07-2021 Through 14-07-2021",

year = "2021",

month = jul,

day = "7",

doi = "10.1145/3449726.3463279",

language = "English",

pages = "13--14",

booktitle = "GECCO '21",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

url = "https://gecco-2021.sigevo.org/HomePage",

}

Bliek, L, Guijt, A & Karlsson, R 2021, Hospital simulation model optimisation with a random ReLU expansion surrogate model. in GECCO '21 : Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, blz. 13-14, 2021 Genetic and Evolutionary Computation Conference, GECCO 2021, Lille, Frankrijk, 10/07/21. https://doi.org/10.1145/3449726.3463279

Hospital simulation model optimisation with a random ReLU expansion surrogate model. / Bliek, Laurens; Guijt, Arthur; Karlsson, Rickard.
GECCO '21 : Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2021. blz. 13-14.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

TY - GEN

T1 - Hospital simulation model optimisation with a random ReLU expansion surrogate model

AU - Bliek, Laurens

AU - Guijt, Arthur

AU - Karlsson, Rickard

PY - 2021/7/7

Y1 - 2021/7/7

N2 - The industrial challenge of the GECCO 2021 conference is an expensive optimisation problem, where the parameters of a hospital simulation model need to be tuned to optimality. We show how a surrogate-based optimisation framework, with a random ReLU expansion as the surrogate model, outperforms other methods such as Bayesian optimisation, Hyperopt, and random search on this problem.

AB - The industrial challenge of the GECCO 2021 conference is an expensive optimisation problem, where the parameters of a hospital simulation model need to be tuned to optimality. We show how a surrogate-based optimisation framework, with a random ReLU expansion as the surrogate model, outperforms other methods such as Bayesian optimisation, Hyperopt, and random search on this problem.

KW - expensive optimisation

KW - simulation optimisation

KW - surrogate models

UR - http://www.scopus.com/inward/record.url?scp=85111011783&partnerID=8YFLogxK

U2 - 10.1145/3449726.3463279

DO - 10.1145/3449726.3463279

M3 - Conference contribution

AN - SCOPUS:85111011783

SP - 13

EP - 14

BT - GECCO '21

PB - Association for Computing Machinery, Inc

T2 - 2021 Genetic and Evolutionary Computation Conference, GECCO 2021

Y2 - 10 July 2021 through 14 July 2021

ER -

Hospital simulation model optimisation with a random ReLU expansion surrogate model

Samenvatting

Congres

Bibliografische nota

Duurzame ontwikkelingsdoelstellingen van de VN

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit