Combining Model and Parameter Uncertainty in Bayesian Neural Networks
This addresses a bottleneck in Bayesian deep learning for researchers and practitioners seeking uncertainty quantification and model compression.
The paper tackles the lack of scalable techniques for combining model and parameter uncertainty in Bayesian neural networks by introducing inference in the joint space of models and parameters, resulting in drastic sparsification of BNN structures.
Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using Bayesian approach: Parameter and prediction uncertainty become easily available, facilitating rigid statistical analysis. Furthermore, prior knowledge can be incorporated. However so far there have been no scalable techniques capable of combining both model (structural) and parameter uncertainty. In this paper we introduce the concept of model uncertainty in BNNs and hence make inference in the joint space of models and parameters. Moreover, we suggest an adaptation of a scalable variational inference approach with reparametrization of marginal inclusion probabilities to incorporate the model space constraints. Finally, we show that incorporating model uncertainty via Bayesian model averaging and Bayesian model selection allows to drastically sparsify the structure of BNNs.