Improving prediction from stochastic simulation via model discrepancy learning

Henry Lam, Xinyu Zhang, Matthew Plumlee

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

Abstract

Stochastic simulation is an indispensable tool in operations and management applications. However, simulation models are only approximations to reality, and often bear discrepancies with the generating processes of real output data. We investigate a framework to statistically learn these discrepancies under the presence of data on past implemented system configurations, which allows us to improve prediction using simulation models. We focus on the case of general continuous output data that generalizes previous work. Our approach utilizes (a combination of) regression analysis and optimization formulations constrained on suitable summary statistics. We demonstrate our approach with a numerical example.

Original languageEnglish (US)
Title of host publication2017 Winter Simulation Conference, WSC 2017
EditorsVictor Chan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1808-1819
Number of pages12
ISBN (Electronic)9781538634288
DOIs
StatePublished - Jan 4 2018
Event2017 Winter Simulation Conference, WSC 2017 - Las Vegas, United States
Duration: Dec 3 2017Dec 6 2017

Publication series

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

Other

Other2017 Winter Simulation Conference, WSC 2017
CountryUnited States
CityLas Vegas
Period12/3/1712/6/17

Fingerprint

Stochastic Simulation
Discrepancy
Stochastic Model
Simulation Model
Prediction
Regression analysis
Output
Statistics
Regression Analysis
Prediction Model
Numerical Examples
Generalise
Configuration
Optimization
Formulation
Approximation
Demonstrate
Learning

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Lam, H., Zhang, X., & Plumlee, M. (2018). Improving prediction from stochastic simulation via model discrepancy learning. In V. Chan (Ed.), 2017 Winter Simulation Conference, WSC 2017 (pp. 1808-1819). (Proceedings - Winter Simulation Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2017.8247918
Lam, Henry ; Zhang, Xinyu ; Plumlee, Matthew. / Improving prediction from stochastic simulation via model discrepancy learning. 2017 Winter Simulation Conference, WSC 2017. editor / Victor Chan. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1808-1819 (Proceedings - Winter Simulation Conference).
@inproceedings{634697f4607a41938f6cc71db3aea63b,
title = "Improving prediction from stochastic simulation via model discrepancy learning",
abstract = "Stochastic simulation is an indispensable tool in operations and management applications. However, simulation models are only approximations to reality, and often bear discrepancies with the generating processes of real output data. We investigate a framework to statistically learn these discrepancies under the presence of data on past implemented system configurations, which allows us to improve prediction using simulation models. We focus on the case of general continuous output data that generalizes previous work. Our approach utilizes (a combination of) regression analysis and optimization formulations constrained on suitable summary statistics. We demonstrate our approach with a numerical example.",
author = "Henry Lam and Xinyu Zhang and Matthew Plumlee",
year = "2018",
month = "1",
day = "4",
doi = "10.1109/WSC.2017.8247918",
language = "English (US)",
series = "Proceedings - Winter Simulation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1808--1819",
editor = "Victor Chan",
booktitle = "2017 Winter Simulation Conference, WSC 2017",
address = "United States",

}

Lam, H, Zhang, X & Plumlee, M 2018, Improving prediction from stochastic simulation via model discrepancy learning. in V Chan (ed.), 2017 Winter Simulation Conference, WSC 2017. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 1808-1819, 2017 Winter Simulation Conference, WSC 2017, Las Vegas, United States, 12/3/17. https://doi.org/10.1109/WSC.2017.8247918

Improving prediction from stochastic simulation via model discrepancy learning. / Lam, Henry; Zhang, Xinyu; Plumlee, Matthew.

2017 Winter Simulation Conference, WSC 2017. ed. / Victor Chan. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1808-1819 (Proceedings - Winter Simulation Conference).

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

TY - GEN

T1 - Improving prediction from stochastic simulation via model discrepancy learning

AU - Lam, Henry

AU - Zhang, Xinyu

AU - Plumlee, Matthew

PY - 2018/1/4

Y1 - 2018/1/4

N2 - Stochastic simulation is an indispensable tool in operations and management applications. However, simulation models are only approximations to reality, and often bear discrepancies with the generating processes of real output data. We investigate a framework to statistically learn these discrepancies under the presence of data on past implemented system configurations, which allows us to improve prediction using simulation models. We focus on the case of general continuous output data that generalizes previous work. Our approach utilizes (a combination of) regression analysis and optimization formulations constrained on suitable summary statistics. We demonstrate our approach with a numerical example.

AB - Stochastic simulation is an indispensable tool in operations and management applications. However, simulation models are only approximations to reality, and often bear discrepancies with the generating processes of real output data. We investigate a framework to statistically learn these discrepancies under the presence of data on past implemented system configurations, which allows us to improve prediction using simulation models. We focus on the case of general continuous output data that generalizes previous work. Our approach utilizes (a combination of) regression analysis and optimization formulations constrained on suitable summary statistics. We demonstrate our approach with a numerical example.

UR - http://www.scopus.com/inward/record.url?scp=85044545018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044545018&partnerID=8YFLogxK

U2 - 10.1109/WSC.2017.8247918

DO - 10.1109/WSC.2017.8247918

M3 - Conference contribution

T3 - Proceedings - Winter Simulation Conference

SP - 1808

EP - 1819

BT - 2017 Winter Simulation Conference, WSC 2017

A2 - Chan, Victor

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lam H, Zhang X, Plumlee M. Improving prediction from stochastic simulation via model discrepancy learning. In Chan V, editor, 2017 Winter Simulation Conference, WSC 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1808-1819. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2017.8247918