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.
A primer on bayesian neural networks: review and debates
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A PINN approach learns galactic gravitational potentials from acceleration data, achieving sub-percent errors on simulations while outperforming analytic models and retaining interpretability via structured priors.
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.
-
Reconstructing Galactic Gravitational Potentials from Stellar Kinematics with Physics-Informed Neural Networks
A PINN approach learns galactic gravitational potentials from acceleration data, achieving sub-percent errors on simulations while outperforming analytic models and retaining interpretability via structured priors.