Active learning strategies for the estimation of a feasible set defined from a vector output black-box simulator
Abstract
Many industrial problems require the use of black-box numerical simulators, for which it is essential to determine the set of so-called feasible input parameters. A set of parameters is feasible if the output of the code on these parameters satisfies given constraints, for example, by remaining below a certain threshold. Active learning is an effective approach to solve this type of problem, by sequentially enriching a design of experiments using a well-chosen acquisition criterion, based here on a Gaussian process surrogate model. In this work, we focus specifically on simulators with vector outputs. We propose several enrichment strategies to simultaneously explore the entire collection of feasible sets associated with each output component. These enrichment strategies are first tested and compared on analytical test functions, before being applied to the pre-calibration of a simulator dedicated to wind turbine design. The aim is to identify input parameter configurations that respect the vibration constraints imposed on the simulator outputs. Numerical results demonstrate the efficiency of the three proposed strategies, which are compared against two baseline strategies (random sampling and Sobol’ sequence).
Related
- Adaptive Bregman Alternating Projections for Feasible Gromov-Wasserstein Learning
- Active learning strategy for excursion-set confidence regions of functional simulator outputs
- Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
- LettuceVisSim: A Simulator That Generates Lettuce Image Time-series for Vision-Based Reinforcement Learning
- Active learning confidence measures for coupling strategies in digital twins integrating simulation and data-driven submodels
BibTeX
@article{duhamel2026active,
title = {{Active learning strategies for the estimation of a feasible set defined from a vector output black-box simulator}},
author = {Clément Duhamel and Céline Helbert and Miguel Munoz Zuniga and Clémentine Prieur and Delphine Sinoquet},
journal = {SMAI Journal of Computational Mathematics},
year = {2026},
month = aug,
doi = {10.5802/smai-jcm.151},
url = {https://hal.science/hal-04970769v3},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Active learning strategies for the estimation of a feasible set defined from a vector output black-box simulator
AU - Clément Duhamel
AU - Céline Helbert
AU - Miguel Munoz Zuniga
AU - Clémentine Prieur
AU - Delphine Sinoquet
PY - 2026
DA - 2026/08/26
JO - SMAI Journal of Computational Mathematics
DO - 10.5802/smai-jcm.151
UR - https://hal.science/hal-04970769v3
AB - Many industrial problems require the use of black-box numerical simulators, for which it is essential to determine the set of so-called feasible input parameters. A set of parameters is feasible if the output of the code on these parameters satisfies given constraints, for example, by remaining below a certain threshold. Active learning is an effective approach to solve this type of problem, by sequentially enriching a design of experiments using a well-chosen acquisition criterion, based here on a Gaussian process surrogate model. In this work, we focus specifically on simulators with vector outputs. We propose several enrichment strategies to simultaneously explore the entire collection of feasible sets associated with each output component. These enrichment strategies are first tested and compared on analytical test functions, before being applied to the pre-calibration of a simulator dedicated to wind turbine design. The aim is to identify input parameter configurations that respect the vibration constraints imposed on the simulator outputs. Numerical results demonstrate the efficiency of the three proposed strategies, which are compared against two baseline strategies (random sampling and Sobol’ sequence).
SN - 2426-8399
ER -