Applying the R2D2 shrinkage prior to Bayesian neural network weights, with a variational Gibbs inference scheme, improves prediction and out-of-distribution detection in image tasks.
Dirichlet–laplace priors for optimal shrinkage.Journal of the American Statistical Association, 110(512):1479–1490, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior
Applying the R2D2 shrinkage prior to Bayesian neural network weights, with a variational Gibbs inference scheme, improves prediction and out-of-distribution detection in image tasks.