Calibrating Deep Convolutional Gaussian Processes

[edit]

Gia-Lac Tran, Edwin Bonilla, John Cunningham, Pietro Michiardi, Maurizio Filippone ;
Proceedings of Machine Learning Research, PMLR 89:1554-1563, 2019.

Abstract

The wide adoption of Convolutional Neural Networks CNNs in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes GPs has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.

Related Material