Multifidelity Monte Carlo estimation with adaptive low-fidelity models

Benjamin Peherstorfer

Research output: Contribution to journalArticle

Abstract

Multifidelity Monte Carlo (MFMC) estimation combines low- and high-fidelity models to speed up the estimation of statistics of the high-fidelity model outputs. MFMC optimally samples the lowand high-fidelity models such that the MFMC estimator has minimal mean-squared error (MSE) for a given computational budget. In the setup of MFMC, the low-fidelity models are static; i.e., they are given and fixed and cannot be changed and adapted. We introduce the adaptive MFMC (AMFMC) method that splits the computational budget between adapting the low-fidelity models to improve their approximation quality and sampling the low- and high-fidelity models to reduce the MSE of the estimator. Our AMFMC approach derives the quasi-optimal balance between adaptation and sampling in the sense that our approach minimizes an upper bound of the MSE, instead of the error directly. We show that the quasi-optimal number of adaptations of the low-fidelity models is bounded even in the limit of an infinite budget. This shows that adapting low-fidelity models in MFMC beyond a certain approximation accuracy is unnecessary and can even be wasteful. Our AMFMC approach trades off adaptation and sampling and so avoids overadaptation of the low- fidelity models. Besides the costs of adapting low-fidelity models, our AMFMC approach can also take into account the costs of the initial construction of the low-fidelity models ("offline costs"), which is critical if low-fidelity models are computationally expensive to build such as reduced models and data-fit surrogate models. Numerical results demonstrate that our adaptive approach can achieve orders of magnitude speedups compared to MFMC estimators with static low-fidelity models and compared to Monte Carlo estimators that use the high-fidelity model alone.

Original languageEnglish (US)
Pages (from-to)579-603
Number of pages25
JournalSIAM-ASA Journal on Uncertainty Quantification
Volume7
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Fidelity
Model
Mean Squared Error
Estimator
Sampling
Costs
Surrogate Model
Reduced Model
Cost Model
Adaptive Method
Approximation
Monte Carlo method
Speedup
Monte Carlo methods
Trade-offs

Keywords

  • Model reduction
  • Monte Carlo
  • Multifidelity
  • Multilevel
  • Surrogate models
  • Uncertainty quantification

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty
  • Discrete Mathematics and Combinatorics
  • Applied Mathematics

Cite this

Multifidelity Monte Carlo estimation with adaptive low-fidelity models. / Peherstorfer, Benjamin.

In: SIAM-ASA Journal on Uncertainty Quantification, Vol. 7, No. 2, 01.01.2019, p. 579-603.

Research output: Contribution to journalArticle

@article{d69e1ede11d54b58a7acee5f79aae3ba,
title = "Multifidelity Monte Carlo estimation with adaptive low-fidelity models",
abstract = "Multifidelity Monte Carlo (MFMC) estimation combines low- and high-fidelity models to speed up the estimation of statistics of the high-fidelity model outputs. MFMC optimally samples the lowand high-fidelity models such that the MFMC estimator has minimal mean-squared error (MSE) for a given computational budget. In the setup of MFMC, the low-fidelity models are static; i.e., they are given and fixed and cannot be changed and adapted. We introduce the adaptive MFMC (AMFMC) method that splits the computational budget between adapting the low-fidelity models to improve their approximation quality and sampling the low- and high-fidelity models to reduce the MSE of the estimator. Our AMFMC approach derives the quasi-optimal balance between adaptation and sampling in the sense that our approach minimizes an upper bound of the MSE, instead of the error directly. We show that the quasi-optimal number of adaptations of the low-fidelity models is bounded even in the limit of an infinite budget. This shows that adapting low-fidelity models in MFMC beyond a certain approximation accuracy is unnecessary and can even be wasteful. Our AMFMC approach trades off adaptation and sampling and so avoids overadaptation of the low- fidelity models. Besides the costs of adapting low-fidelity models, our AMFMC approach can also take into account the costs of the initial construction of the low-fidelity models ({"}offline costs{"}), which is critical if low-fidelity models are computationally expensive to build such as reduced models and data-fit surrogate models. Numerical results demonstrate that our adaptive approach can achieve orders of magnitude speedups compared to MFMC estimators with static low-fidelity models and compared to Monte Carlo estimators that use the high-fidelity model alone.",
keywords = "Model reduction, Monte Carlo, Multifidelity, Multilevel, Surrogate models, Uncertainty quantification",
author = "Benjamin Peherstorfer",
year = "2019",
month = "1",
day = "1",
doi = "10.1137/17M1159208",
language = "English (US)",
volume = "7",
pages = "579--603",
journal = "SIAM-ASA Journal on Uncertainty Quantification",
issn = "2166-2525",
publisher = "Society for Industrial and Applied Mathematics Publications",
number = "2",

}

TY - JOUR

T1 - Multifidelity Monte Carlo estimation with adaptive low-fidelity models

AU - Peherstorfer, Benjamin

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Multifidelity Monte Carlo (MFMC) estimation combines low- and high-fidelity models to speed up the estimation of statistics of the high-fidelity model outputs. MFMC optimally samples the lowand high-fidelity models such that the MFMC estimator has minimal mean-squared error (MSE) for a given computational budget. In the setup of MFMC, the low-fidelity models are static; i.e., they are given and fixed and cannot be changed and adapted. We introduce the adaptive MFMC (AMFMC) method that splits the computational budget between adapting the low-fidelity models to improve their approximation quality and sampling the low- and high-fidelity models to reduce the MSE of the estimator. Our AMFMC approach derives the quasi-optimal balance between adaptation and sampling in the sense that our approach minimizes an upper bound of the MSE, instead of the error directly. We show that the quasi-optimal number of adaptations of the low-fidelity models is bounded even in the limit of an infinite budget. This shows that adapting low-fidelity models in MFMC beyond a certain approximation accuracy is unnecessary and can even be wasteful. Our AMFMC approach trades off adaptation and sampling and so avoids overadaptation of the low- fidelity models. Besides the costs of adapting low-fidelity models, our AMFMC approach can also take into account the costs of the initial construction of the low-fidelity models ("offline costs"), which is critical if low-fidelity models are computationally expensive to build such as reduced models and data-fit surrogate models. Numerical results demonstrate that our adaptive approach can achieve orders of magnitude speedups compared to MFMC estimators with static low-fidelity models and compared to Monte Carlo estimators that use the high-fidelity model alone.

AB - Multifidelity Monte Carlo (MFMC) estimation combines low- and high-fidelity models to speed up the estimation of statistics of the high-fidelity model outputs. MFMC optimally samples the lowand high-fidelity models such that the MFMC estimator has minimal mean-squared error (MSE) for a given computational budget. In the setup of MFMC, the low-fidelity models are static; i.e., they are given and fixed and cannot be changed and adapted. We introduce the adaptive MFMC (AMFMC) method that splits the computational budget between adapting the low-fidelity models to improve their approximation quality and sampling the low- and high-fidelity models to reduce the MSE of the estimator. Our AMFMC approach derives the quasi-optimal balance between adaptation and sampling in the sense that our approach minimizes an upper bound of the MSE, instead of the error directly. We show that the quasi-optimal number of adaptations of the low-fidelity models is bounded even in the limit of an infinite budget. This shows that adapting low-fidelity models in MFMC beyond a certain approximation accuracy is unnecessary and can even be wasteful. Our AMFMC approach trades off adaptation and sampling and so avoids overadaptation of the low- fidelity models. Besides the costs of adapting low-fidelity models, our AMFMC approach can also take into account the costs of the initial construction of the low-fidelity models ("offline costs"), which is critical if low-fidelity models are computationally expensive to build such as reduced models and data-fit surrogate models. Numerical results demonstrate that our adaptive approach can achieve orders of magnitude speedups compared to MFMC estimators with static low-fidelity models and compared to Monte Carlo estimators that use the high-fidelity model alone.

KW - Model reduction

KW - Monte Carlo

KW - Multifidelity

KW - Multilevel

KW - Surrogate models

KW - Uncertainty quantification

UR - http://www.scopus.com/inward/record.url?scp=85068771808&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068771808&partnerID=8YFLogxK

U2 - 10.1137/17M1159208

DO - 10.1137/17M1159208

M3 - Article

AN - SCOPUS:85068771808

VL - 7

SP - 579

EP - 603

JO - SIAM-ASA Journal on Uncertainty Quantification

JF - SIAM-ASA Journal on Uncertainty Quantification

SN - 2166-2525

IS - 2

ER -