MFVI in BNNs underestimates uncertainty between data regions, leading to overconfident OOD predictions, while linearised Laplace approximation performs better.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Empirical comparison of ten BNN inference methods shows test log-likelihood can mislead on uncertainty quality and that posterior-structure innovations do not necessarily yield high-quality approximations.
citing papers explorer
-
'In-Between' Uncertainty in Bayesian Neural Networks
MFVI in BNNs underestimates uncertainty between data regions, leading to overconfident OOD predictions, while linearised Laplace approximation performs better.
-
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Empirical comparison of ten BNN inference methods shows test log-likelihood can mislead on uncertainty quality and that posterior-structure innovations do not necessarily yield high-quality approximations.