Reviews: Predictive Uncertainty Estimation via Prior Networks

The authors develop prior networks, an approach to identifying misclassification on in and out of distribution examples. The work largely builds upon Malinin et al, 2017, adapting their method to the Dirichlet case. The experiments are simple but lack controls and may be too simple to validate the method. Overall: Quality: There do not appear to be any obvious errors. There is no model uncertainty in this paper as a dirac is used for the model prior, so why spend time talkimg about it?