TY - JOUR
T1 - Combining multiple surrogate models to accelerate failure probability estimation with expensive high-fidelity models
AU - Peherstorfer, Benjamin
AU - Kramer, Boris
AU - Willcox, Karen
N1 - Funding Information:
This work was supported by the DARPA EQUiPS Program, Award UTA15-001067, Program Manager F. Fahroo, and by the AFOSR MURI on multi-information sources of multi-physics systems, Award Number FA9550-15-1-0038, Program Manager J.-L. Cambier. Several examples were computed on the computer clusters of the Munich Centre of Advanced Computing.
Publisher Copyright:
© 2017 Elsevier Inc.
PY - 2017/7/15
Y1 - 2017/7/15
N2 - In failure probability estimation, importance sampling constructs a biasing distribution that targets the failure event such that a small number of model evaluations is sufficient to achieve a Monte Carlo estimate of the failure probability with an acceptable accuracy; however, the construction of the biasing distribution often requires a large number of model evaluations, which can become computationally expensive. We present a mixed multifidelity importance sampling (MMFIS) approach that leverages computationally cheap but erroneous surrogate models for the construction of the biasing distribution and that uses the original high-fidelity model to guarantee unbiased estimates of the failure probability. The key property of our MMFIS estimator is that it can leverage multiple surrogate models for the construction of the biasing distribution, instead of a single surrogate model alone. We show that our MMFIS estimator has a mean-squared error that is up to a constant lower than the mean-squared errors of the corresponding estimators that uses any of the given surrogate models alone—even in settings where no information about the approximation qualities of the surrogate models is available. In particular, our MMFIS approach avoids the problem of selecting the surrogate model that leads to the estimator with the lowest mean-squared error, which is challenging if the approximation quality of the surrogate models is unknown. We demonstrate our MMFIS approach on numerical examples, where we achieve orders of magnitude speedups compared to using the high-fidelity model only.
AB - In failure probability estimation, importance sampling constructs a biasing distribution that targets the failure event such that a small number of model evaluations is sufficient to achieve a Monte Carlo estimate of the failure probability with an acceptable accuracy; however, the construction of the biasing distribution often requires a large number of model evaluations, which can become computationally expensive. We present a mixed multifidelity importance sampling (MMFIS) approach that leverages computationally cheap but erroneous surrogate models for the construction of the biasing distribution and that uses the original high-fidelity model to guarantee unbiased estimates of the failure probability. The key property of our MMFIS estimator is that it can leverage multiple surrogate models for the construction of the biasing distribution, instead of a single surrogate model alone. We show that our MMFIS estimator has a mean-squared error that is up to a constant lower than the mean-squared errors of the corresponding estimators that uses any of the given surrogate models alone—even in settings where no information about the approximation qualities of the surrogate models is available. In particular, our MMFIS approach avoids the problem of selecting the surrogate model that leads to the estimator with the lowest mean-squared error, which is challenging if the approximation quality of the surrogate models is unknown. We demonstrate our MMFIS approach on numerical examples, where we achieve orders of magnitude speedups compared to using the high-fidelity model only.
KW - Failure probability estimation
KW - Model reduction
KW - Multifidelity
KW - Rare event simulation
KW - Surrogate modeling
KW - Uncertainty quantification
UR - http://www.scopus.com/inward/record.url?scp=85017470466&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85017470466&partnerID=8YFLogxK
U2 - 10.1016/j.jcp.2017.04.012
DO - 10.1016/j.jcp.2017.04.012
M3 - Article
AN - SCOPUS:85017470466
VL - 341
SP - 61
EP - 75
JO - Journal of Computational Physics
JF - Journal of Computational Physics
SN - 0021-9991
ER -