Poster
in
Workshop: Bayesian Decision-making and Uncertainty: from probabilistic and spatiotemporal modeling to sequential experiment design

Big Batch Bayesian Active Learning by Considering Predictive Probabilities

Sebastian Ober · Sam Power · Tom Diethe · Henry Moss

Keywords: Gaussian Processes bayesian active learning Bayesian deep learning

Project Page [ OpenReview]

Abstract

We observe that BatchBALD, a popular acquisition function for batch Bayesian active learning for classification, can conflate epistemic and aleatoric uncertainty, leading to suboptimal performance. Motivated by this observation, we propose to focus on the predictive probabilities, which only exhibit epistemic uncertainty. The result is an acquisition function that not only performs better, but is also faster to evaluate, allowing for larger batches than before.

Chat is not available.