Emulation of stochastic simulators using generalized lambda models

DOI10.1137/20M1337302MaRDI QIDQ5158924zbMATH OpenFDO

Authors Xujia Zhu, Bruno Sudret

Publication date 26 October 2021

Published in SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2007.00996

zbMATH Keywords

surrogate modelingpolynomial chaos expansionsstochastic simulatorsgeneralized lambda distributions

Mathematics Subject Classification ID

Parametric inference (62F99) Approximations to statistical distributions (nonasymptotic) (62E17) Reasoning under uncertainty in the context of artificial intelligence (68T37) Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10)

Abstract: Stochastic simulators are ubiquitous in many fields of applied sciences and engineering. In the context of uncertainty quantification and optimization, a large number of simulations is usually necessary, which becomes intractable for high-fidelity models. Thus surrogate models of stochastic simulators have been intensively investigated in the last decade. In this paper, we present a novel approach to surrogating the response distribution of a stochastic simulator which uses generalized lambda distributions, whose parameters are represented by polynomial chaos expansions of the model inputs. As opposed to most existing approaches, this new method does not require replicated runs of the simulator at each point of the experimental design. We propose a new fitting procedure which combines maximum conditional likelihood estimation with (modified) feasible generalized least-squares. We compare our method with state-of-the-art nonparametric kernel estimation on four different applications stemming from mathematical finance and epidemiology. Its performance is illustrated in terms of the accuracy of both the mean/variance of the stochastic simulator and the response distribution. As the proposed approach can also be used with experimental designs containing replications, we carry out a comparison on two of the examples, showing that replications do not necessarily help to get a better overall accuracy and may even worsen the results (at a fixed total number of runs of the simulator).

Recommendations

• Emulators for stochastic simulation codes
• Gaussian process emulators for the stochastic finite element method
• Using emulators to estimate uncertainty in complex models
• Bayesian calibration of multistate stochastic simulators
• Stochastic kriging for simulation metamodeling

Cites work

• scientific article; zbMATH DE number 991833 (Why is no real title available?)
• scientific article; zbMATH DE number 3782216 (Why is no real title available?)
• scientific article; zbMATH DE number 47282 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 2135362 (Why is no real title available?)
• scientific article; zbMATH DE number 2107939 (Why is no real title available?)
• scientific article; zbMATH DE number 2231189 (Why is no real title available?)
• A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
• Adaptive sparse polynomial chaos expansion based on least angle regression
• An extended quasi-likelihood function
• Calibrating a stochastic, agent-based model using quantile-based emulation
• Data-driven polynomial chaos expansion for machine learning regression
• Dimension reduction and adaptation in conditional density estimation
• Emulators for stochastic simulation codes
• Estimating Regression Models with Multiplicative Heteroscedasticity
• Fitting statistical distributions. The generalized lambda distribution and generalized bootstrap methods
• Gaussian processes for machine learning.
• Global sensitivity analysis of stochastic computer models with joint metamodels
• Introduction to nonparametric estimation
• Large Sample Properties of Generalized Method of Moments Estimators
• Nonintrusive polynomial chaos expansions for sensitivity analysis in stochastic differential equations
• On the convergence of generalized polynomial chaos expansions
• Physical Systems with Random Uncertainties: Chaos Representations with Arbitrary Probability Measure
• Polynomial chaos expansions for dependent random variables
• Practical Heteroscedastic Gaussian Process Modeling for Large Simulation Experiments
• REPLICATION-BASED EMULATION OF THE RESPONSE DISTRIBUTION OF STOCHASTIC SIMULATORS USING GENERALIZED LAMBDA DISTRIBUTIONS
• SURROGATE MODELING OF STOCHASTIC FUNCTIONS-APPLICATION TO COMPUTATIONAL ELECTROMAGNETIC DOSIMETRY
• Stochastic calculus for finance. II: Continuous-time models.
• Stochastic epidemic models: a survey
• Stochastic kriging for simulation metamodeling
• The Conjugate Gradient Method and Trust Regions in Large Scale Optimization
• The Glivenko-Cantelli problem
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Variance Function Estimation
• a study of the generalized tukey lambda family

Cited in

(4)

• Polynomial chaos surrogate construction for random fields with parametric uncertainty
• Emulators for stochastic simulation codes
• Reweighting samples under covariate shift using a Wasserstein distance criterion
• A spectral surrogate model for stochastic simulators computed from trajectory samples

Describes a project that uses

Uses Software

• UQLab
• OPQ
• QRM
• np

This page was built for publication: Emulation of stochastic simulators using generalized lambda models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5158924)