A hyperprior on the effective output variance of deep ReLU Bayesian neural networks yields simultaneously admissible and minimax decision rules in the normal location model under quadratic loss.
Goodness of prediction fit.Biometrika, 62(3):547–554, 1975
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Minimaxity and Admissibility of Bayesian Neural Networks
A hyperprior on the effective output variance of deep ReLU Bayesian neural networks yields simultaneously admissible and minimax decision rules in the normal location model under quadratic loss.