Gaussian process emulators (GPE) are a machine learning approach that replicates computational demanding models using training runs of that model. Constructing such a surrogate is very challenging and in the context of Bayesian inference, the training runs should be well invested. The current paper offers a fully Bayesian view on GPEs for Bayesian inference accompanied by Bayesian active learning (BAL). We introduce three BAL strategies that adaptively identify training sets for the GPE using information-theoretic arguments (Oladyshkin and Nowak, 2019). The first strategy relies on Bayesian model evidence that indicates the GPE's quality of matching the measurement data, the second strategy is based on relative entropy that indicates the relative information gain for the GPE, and the third is founded on information entropy that indicates the missing information in the GPE. The BAL-GPE Matlab Toolbox offers a fully Bayesian view (Oladyshkin, Mohammadi, Kroeker and Nowak, 2020) on GPE through Bayesian inference accompanied by Bayesian active learning (BAL).
Stuttgart Center for Simulation Science,
Department of Stochastic Simulation and Safety Research for Hydrosystems,
Institute for Modelling Hydraulic and Environmental Systems,
University of Stuttgart, Pfaffenwaldring 5a, 70569 Stuttgart
Sergey Oladyshkin (2020). BAL-GPE Matlab Toolbox: Bayesian Active Learning for GPE (https://www.mathworks.com/matlabcentral/fileexchange/74794-bal-gpe-matlab-toolbox-bayesian-active-learning-for-gpe), MATLAB Central File Exchange. Retrieved .
Full BAL-GPE Version based on Oladyshkin, Mohammadi, Kroeker and Nowak, 2020 (https://www.mdpi.com/1099-4300/22/8/890)