Bayesian optimal experimental design (BOED) is a principled framework for making efficient use of limited experimental resources. Unfortunately, its applicability is hampered by the difficulty of obtaining accurate estimates of the expected information gain (EIG) of an experiment. To address this, we introduce several classes of fast EIG estimators suited to the experiment design context by building on ideas from variational inference and mutual information estimation. We show theoretically and empirically that these estimators can provide significant gains in speed and accuracy over previous approaches. We demonstrate the practicality of our approach via a number of experiments, including an adaptive experiment with human participants.
READ FULL TEXT
A simple project, which explores the variational estimators of Foster (https://arxiv.org/abs/1903.05480) in a Bayesian linear regression setting. Using nested Monte Carlo estimators the exact (convex) information gain is calculated for the regression.
share