Black-box mixed-variable optimisation using a surrogate model that satisfies integer constraints

Laurens Bliek, Arthur Guijt, Sicco Verwer, Mathijs de Weerdt

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

A challenging problem in both engineering and computer science is that of minimising a function for which we have no mathematical formulation available, that is expensive to evaluate, and that contains continuous and integer variables, for example in automatic algorithm configuration. Surrogate-based algorithms are very suitable for this type of problem, but most existing techniques are designed with only continuous or only discrete variables in mind. Mixed-Variable ReLU-based Surrogate Modelling (MVRSM) is a surrogate-based algorithm that uses a linear combination of rectified linear units, defined in such a way that (local) optima satisfy the integer constraints. Unlike other methods, it also has a constant run-time per iteration. This method outperforms the state of the art on several synthetic benchmarks with up to 238 continuous and integer variables, and achieves competitive performance on two real-life benchmarks: XG-Boost hyperparameter tuning and Electrostatic Precipitator optimisation.

Originele taal-2Engels
TitelGECCO'21
SubtitelProceedings of the 2021 Genetic and Evolutionary Computation Conference Companion
UitgeverijAssociation for Computing Machinery, Inc
Pagina's1851-1859
Aantal pagina's9
ISBN van elektronische versie9781450383516
DOI's
StatusGepubliceerd - 7 jul 2021
Evenement2021 Genetic and Evolutionary Computation Conference, GECCO 2021 - Virtual, Virtual, Online, Frankrijk
Duur: 10 jul 202114 jul 2021
https://gecco-2021.sigevo.org/HomePage

Congres

Congres2021 Genetic and Evolutionary Computation Conference, GECCO 2021
Verkorte titelGECCO 2021
Land/RegioFrankrijk
StadVirtual, Online
Periode10/07/2114/07/21
Internet adres

Bibliografische nota

Publisher Copyright:
© 2021 Owner/Author.

Vingerafdruk

Duik in de onderzoeksthema's van 'Black-box mixed-variable optimisation using a surrogate model that satisfies integer constraints'. Samen vormen ze een unieke vingerafdruk.

Citeer dit