Response probability distribution estimation of expensive computer simulators: A Bayesian active learning perspective using Gaussian process regression

• Published in: Structural safety Vol. 114; p. 102579
• Main Authors: Dang, Chao, Valdebenito, Marcos A., Manque, Nataly A., Xu, Jun, Faes, Matthias G.R.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2025
• Subjects: Bayesian active learning; Bayesian inference; Computer simulator; Gaussian process regression; Probability distribution estimation; Gaussian process regression; Computer simulator; Bayesian active learning; Bayesian inference; Probability distribution estimation
• DOI: 10.1016/j.strusafe.2025.102579
• ISSN: 0167-4730

Estimation of the response probability distributions of computer simulators subject to input random variables is a crucial task in many fields. However, achieving this task with guaranteed accuracy remains an open computational challenge, especially for expensive-to-evaluate computer simulators. In this work, a Bayesian active learning perspective is presented to address the challenge, which is based on the use of the Gaussian process (GP) regression. First, estimation of the response probability distributions is conceptually interpreted as a Bayesian inference problem, as opposed to frequentist inference. This interpretation provides several important benefits: (1) it quantifies and propagates discretization error probabilistically; (2) it incorporates prior knowledge of the computer simulator, and (3) it enables the effective reduction of numerical uncertainty in the solution to a prescribed level. The conceptual Bayesian idea is then realized by using the GP regression, where we derive the posterior statistics of the response probability distributions in semi-analytical form and also provide a numerical solution scheme. Based on the practical Bayesian approach, a Bayesian active learning (BAL) method is further proposed for estimating the response probability distributions. In this context, the key contribution lies in the development of two crucial components for active learning, i.e., stopping criterion and learning function, by taking advantage of the posterior statistics. It is empirically demonstrated by five numerical examples that the proposed BAL method can efficiently estimate the response probability distributions with desired accuracy. •Response probability distribution estimation is conceptually interpreted as a Bayesian inference problem.•A practical Bayesian approach is developed based on Gaussian process regression.•A Bayesian active learning method is proposed based on the practical Bayesian approach.•Stopping criterion and learning function are developed using the posterior statistics.•Five numerical examples illustrate the good performance of the proposed method.