A von Mises-Fisher posterior on weight directions, matched to normalized networks, yields a per-layer effective noise parameter with a closed-form dimension-aware KL that improves calibration on CIFAR-10.
On calibration of modern neural networks.International Conference on Machine Learning, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Precise Bayesian Neural Networks
A von Mises-Fisher posterior on weight directions, matched to normalized networks, yields a per-layer effective noise parameter with a closed-form dimension-aware KL that improves calibration on CIFAR-10.