Adaptive Design of Experiments for Conservative Estimation of Excursion Sets

Abstract : We consider a Gaussian process model trained on few evaluations of an expensive-to-evaluate deterministic function and we study the problem of estimating a fixed excursion set of this function. We focus on conservative estimates as they allow control on false positives while minimizing false negatives. We introduce adaptive strategies that sequentially selects new evaluations of the function by reducing the uncertainty on conservative estimates. Following the Stepwise Uncertainty Reduction approach we obtain new evaluations by minimizing adapted criteria. We provide tractable formulae for the conservative criteria and we benchmark the method on random functions generated under the model assumptions in two and five dimensions. Finally the method is applied to a reliability engineering test case. Overall, the proposed strategy of minimizing false negatives in conservative estimation achieves competitive performance both in terms of model based and a-posteriori indicators.
Complete list of metadatas
Contributor : Azzimonti Dario <>
Submitted on : Monday, April 9, 2018 - 9:44:29 AM
Last modification on : Tuesday, February 18, 2020 - 10:54:01 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License


  • HAL Id : hal-01379642, version 3
  • ARXIV : 1611.07256


Dario Azzimonti, David Ginsbourger, Clément Chevalier, Julien Bect, Yann Richet. Adaptive Design of Experiments for Conservative Estimation of Excursion Sets. 2018. ⟨hal-01379642v3⟩



Record views


Files downloads