Skip to yearly menu bar Skip to main content


Poster

Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

Christos Louizos · Max Welling

Gallery #70

Abstract:

We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employing normalizing flows while still allowing for local reparametrizations and a tractable lower bound. In experiments we show that with this new approximation we can significantly improve upon classical mean field for Bayesian neural networks on both predictive accuracy as well as predictive uncertainty.

Live content is unavailable. Log in and register to view live content