Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect Lorenzo Noci Dept of Computer Science ETH Zürich lorenzo.noci@inf.ethz.ch Kevin Roth

Neural Information Processing Systems 

The " cold posterior effect " (CPE) in Bayesian deep learning describes the uncom-forting observation that the predictive performance of Bayesian neural networks

Similar Docs  Excel Report  more

TitleSimilaritySource
None found