NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:805
Title:Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift

The reviewers all considered the author feedback and discussed the paper thoroughly. Most concerns could thereby be clarified and the main point against accepting the paper is a lack of comparison with approaches not based on two-sample tests like [17,19]. If these could be included in a camera-ready-copy, that would be great; but even without it, I consider the contribution sufficient to justify accepting the paper as a poster.