Approximately optimal experimental design for heteroscedastic Gaussian process models
Alexios Boukouvalas, Dan Cornford, Milan Stehlík · Aston Publications Explorer (Aston University) · 2009
This paper presents a greedy Bayesian experimental design criterion for heteroscedastic Gaussian process models. The criterion is based on the Fisher information and is optimal in the sense of minimizing parameter uncertainty for likelihood based estimators. We demonstrate the validity of the criterion under different noise regimes and present experimental results from a rabies simulator to demonstrate the effectiveness of the resulting approximately optimal designs.