Alpha-divergence minimization with mixed variational posterior for Bayesian neural networks and its robustness against adversarial examples
Neurocomputing, pp. 427-434, 2021.
Abstract In the approximate inference of Bayesian neural networks (BNNs), the variational posterior distribution is often taken an exponential family form (such as Gaussian). We propose to make the mixtures of exponential family distributions instead to get a more flexible approximation posterior. A novel reparameterization trick is int...More
Full Text (Upload PDF)
PPT (Upload PPT)