Abstract

Multi-fidelity simulation optimization is an emerging area looking at the use of low-fidelity (computationally cheap but inaccurate) models to optimize high-fidelity (expensive and accurate) models. In this context, low-fidelity models exhibit a mismatch to high-fidelity models whose values can be point-wise obtained by querying an expensive simulator. Herein, an efficient multi-fidelity algorithm is proposed for continuous global optimization. The algorithm is made up of an additive model that consolidates low-fidelity and bias (mismatch) predictions. Two sampling criteria with different use of the cumulated high and low-fidelity information are introduced as well as a cheap certificate guiding the decision on whether to sample from the expensive simulator. The performance of proposed algorithms is evaluated using a state of the art stochastic search benchmark algorithm. The results show that the proposed methods can beat the benchmark with improved accuracy, while essentially maintaining the same performance in terms of number of expensive simulations.

Original languageEnglish (US)
Title of host publicationWSC 2018 - 2018 Winter Simulation Conference
Subtitle of host publicationSimulation for a Noble Cause
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2131-2142
Number of pages12
ISBN (Electronic)9781538665725
DOIs
StatePublished - Jan 31 2019
Event2018 Winter Simulation Conference, WSC 2018 - Gothenburg, Sweden
Duration: Dec 9 2018Dec 12 2018

Publication series

NameProceedings - Winter Simulation Conference
Volume2018-December
ISSN (Print)0891-7736

Conference

Conference2018 Winter Simulation Conference, WSC 2018
CountrySweden
CityGothenburg
Period12/9/1812/12/18

Fingerprint

Simulation Optimization
Continuous Optimization
Gaussian Process
Fidelity
Regression
Simulators
Model
Global optimization
Simulator
Benchmark
Stochastic Search
Additive Models
Sampling
Beat
Certificate
Inaccurate
Global Optimization
Optimise
Prediction

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Inanlouganji, A., Pedrielli, G., Fainekos, G., & Pokutta, S. (2019). Continuous simulation optimization with model mismatch using Gaussian process regression. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause (pp. 2131-2142). [8632427] (Proceedings - Winter Simulation Conference; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2018.8632427

Continuous simulation optimization with model mismatch using Gaussian process regression. / Inanlouganji, Alireza; Pedrielli, Giulia; Fainekos, Georgios; Pokutta, Sebastian.

WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2131-2142 8632427 (Proceedings - Winter Simulation Conference; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Inanlouganji, A, Pedrielli, G, Fainekos, G & Pokutta, S 2019, Continuous simulation optimization with model mismatch using Gaussian process regression. in WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause., 8632427, Proceedings - Winter Simulation Conference, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 2131-2142, 2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, 12/9/18. https://doi.org/10.1109/WSC.2018.8632427
Inanlouganji A, Pedrielli G, Fainekos G, Pokutta S. Continuous simulation optimization with model mismatch using Gaussian process regression. In WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2131-2142. 8632427. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2018.8632427
Inanlouganji, Alireza ; Pedrielli, Giulia ; Fainekos, Georgios ; Pokutta, Sebastian. / Continuous simulation optimization with model mismatch using Gaussian process regression. WSC 2018 - 2018 Winter Simulation Conference: Simulation for a Noble Cause. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2131-2142 (Proceedings - Winter Simulation Conference).
@inproceedings{f588eea036d04f158cc0d6166e39c647,
title = "Continuous simulation optimization with model mismatch using Gaussian process regression",
abstract = "Multi-fidelity simulation optimization is an emerging area looking at the use of low-fidelity (computationally cheap but inaccurate) models to optimize high-fidelity (expensive and accurate) models. In this context, low-fidelity models exhibit a mismatch to high-fidelity models whose values can be point-wise obtained by querying an expensive simulator. Herein, an efficient multi-fidelity algorithm is proposed for continuous global optimization. The algorithm is made up of an additive model that consolidates low-fidelity and bias (mismatch) predictions. Two sampling criteria with different use of the cumulated high and low-fidelity information are introduced as well as a cheap certificate guiding the decision on whether to sample from the expensive simulator. The performance of proposed algorithms is evaluated using a state of the art stochastic search benchmark algorithm. The results show that the proposed methods can beat the benchmark with improved accuracy, while essentially maintaining the same performance in terms of number of expensive simulations.",
author = "Alireza Inanlouganji and Giulia Pedrielli and Georgios Fainekos and Sebastian Pokutta",
year = "2019",
month = "1",
day = "31",
doi = "10.1109/WSC.2018.8632427",
language = "English (US)",
series = "Proceedings - Winter Simulation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2131--2142",
booktitle = "WSC 2018 - 2018 Winter Simulation Conference",

}

TY - GEN

T1 - Continuous simulation optimization with model mismatch using Gaussian process regression

AU - Inanlouganji, Alireza

AU - Pedrielli, Giulia

AU - Fainekos, Georgios

AU - Pokutta, Sebastian

PY - 2019/1/31

Y1 - 2019/1/31

N2 - Multi-fidelity simulation optimization is an emerging area looking at the use of low-fidelity (computationally cheap but inaccurate) models to optimize high-fidelity (expensive and accurate) models. In this context, low-fidelity models exhibit a mismatch to high-fidelity models whose values can be point-wise obtained by querying an expensive simulator. Herein, an efficient multi-fidelity algorithm is proposed for continuous global optimization. The algorithm is made up of an additive model that consolidates low-fidelity and bias (mismatch) predictions. Two sampling criteria with different use of the cumulated high and low-fidelity information are introduced as well as a cheap certificate guiding the decision on whether to sample from the expensive simulator. The performance of proposed algorithms is evaluated using a state of the art stochastic search benchmark algorithm. The results show that the proposed methods can beat the benchmark with improved accuracy, while essentially maintaining the same performance in terms of number of expensive simulations.

AB - Multi-fidelity simulation optimization is an emerging area looking at the use of low-fidelity (computationally cheap but inaccurate) models to optimize high-fidelity (expensive and accurate) models. In this context, low-fidelity models exhibit a mismatch to high-fidelity models whose values can be point-wise obtained by querying an expensive simulator. Herein, an efficient multi-fidelity algorithm is proposed for continuous global optimization. The algorithm is made up of an additive model that consolidates low-fidelity and bias (mismatch) predictions. Two sampling criteria with different use of the cumulated high and low-fidelity information are introduced as well as a cheap certificate guiding the decision on whether to sample from the expensive simulator. The performance of proposed algorithms is evaluated using a state of the art stochastic search benchmark algorithm. The results show that the proposed methods can beat the benchmark with improved accuracy, while essentially maintaining the same performance in terms of number of expensive simulations.

UR - http://www.scopus.com/inward/record.url?scp=85062624585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062624585&partnerID=8YFLogxK

U2 - 10.1109/WSC.2018.8632427

DO - 10.1109/WSC.2018.8632427

M3 - Conference contribution

AN - SCOPUS:85062624585

T3 - Proceedings - Winter Simulation Conference

SP - 2131

EP - 2142

BT - WSC 2018 - 2018 Winter Simulation Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -