A Bayesian weight posterior is wrapped into a belief-function posterior via interval masses and a fitted Dirichlet distribution, then used to initialize a Hybrid Interval Neural Network, with reported accuracy and OOD gains that mostly vanish after fine-tuning.
Molina, and Christopher Metzler
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Epistemic Wrapping for Uncertainty Quantification
A Bayesian weight posterior is wrapped into a belief-function posterior via interval masses and a fitted Dirichlet distribution, then used to initialize a Hybrid Interval Neural Network, with reported accuracy and OOD gains that mostly vanish after fine-tuning.