bayesian-neural-networks

This paper proposes a full-covariance smoothing technique for Bayesian neural networks to enable efficient online adaptation by propagating correlations through nonlinear activations, demonstrated in tasks like classification and control.

This paper presents a framework for deploying consistent safety certificates in one-shot federated Bayesian models by propagating local posterior events through aggregation rules, specifically for Federated Averaging.

This paper studies data augmentation for Bayesian neural networks trained with variational inference, deriving conditions for exact equivariance and introducing novel symmetrization techniques like orbit expansion to improve symmetry and performance.

Proposes EVIDENT, a framework that integrates Bayesian training and evidence-based ranking for neural architecture selection, demonstrated on subject-specific blood glucose forecasting in type 1 diabetes, systematically selecting low-capacity models that generalize reliably.