MFVI in BNNs underestimates uncertainty between data regions, leading to overconfident OOD predictions, while linearised Laplace approximation performs better.
P., Salimans, T., and Welling, M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
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.