Get started
Work

Multivariate Bayesian Last Layer for Regression with Uncertainty Quantification and Decomposition

Year: 2024
Type: preprint
Abstract: We present new Bayesian Last Layer neural network models in the setting of multivariate regression under heteroscedastic noise, and propose EM algorithms for parameter learning. Bayesian modeling of a neural network's final layer has the attractive property of uncertainty quantification with a single forward pass. The proposed framework is capable of disentangling the aleatoric and epistemic uncertainty, and can be used to enhance a canonically trained deep neural network with uncertainty-aware capabilities.
DOI: 10.48550/arxiv.2405.01761
Authors: Wang, Han, Kawasaki, Eiji, Damblin, Guillaume, Daniel, Geoffrey
Institutions: Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, CEA Paris-Saclay - Etablissement de Saclay, Laboratoire d'Intégration des Systèmes et des Technologies, CEA Paris-Saclay, Service de Génie Logiciel pour la Simulation
Language: English
Open Access status: green
OpenAlex ID: W4396778399
Cites:
Cited by:
Related to: 10