NATURAL POSTERIOR NETWORK: DEEP BAYESIAN UNCERTAINTY FOR EXPONENTIAL FAMILY DISTRIBUTIONS

Bertrand Charpentier, Oliver Borchert, Daniel Zügner, Simon Geisler, Stephan Günnemann

Research output: Contribution to conferencePaperpeer-review

10 Scopus citations

Abstract

Uncertainty awareness is crucial to develop reliable machine learning models. In this work, we propose the Natural Posterior Network (NatPN) for fast and high-quality uncertainty estimation for any task where the target distribution belongs to the exponential family. Thus, NatPN finds application for both classification and general regression settings. Unlike many previous approaches, NatPN does not require out-of-distribution (OOD) data at training time. Instead, it leverages Normalizing Flows to fit a single density on a learned low-dimensional and task-dependent latent space. For any input sample, NatPN uses the predicted likelihood to perform a Bayesian update over the target distribution. Theoretically, NatPN assigns high uncertainty far away from training data. Empirically, our extensive experiments on calibration and OOD detection show that NatPN delivers highly competitive performance for classification, regression and count prediction tasks.

Original languageEnglish
StatePublished - 2022
Event10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online
Duration: 25 Apr 202229 Apr 2022

Conference

Conference10th International Conference on Learning Representations, ICLR 2022
CityVirtual, Online
Period25/04/2229/04/22

Fingerprint

Dive into the research topics of 'NATURAL POSTERIOR NETWORK: DEEP BAYESIAN UNCERTAINTY FOR EXPONENTIAL FAMILY DISTRIBUTIONS'. Together they form a unique fingerprint.

Cite this