Sparsifying Bayesian neural networks with latent binary variables and normalizing flows

1 code implementation • 5 May 2023 • Lars Skaaret-Lund, Geir Storvik, Aliaksandr Hubin

In this paper, we will consider two extensions to the LBBNN method: Firstly, by using the local reparametrization trick (LRT) to sample the hidden units directly, we get a more computationally efficient algorithm.

Machine Translation Variable Selection