Review for NeurIPS paper: Quantile Propagation for Wasserstein-Approximate Gaussian Processes

Weaknesses: After reading the rebuttals and reviewer discussion, I realise that I was wrong about EP overestimating the variance and the strength of the paper's empirical results, so I have decided to downgrade my score. I still believe this paper should be accepted, but I'm less confident of the matter. Here are the things I changed my mind about, to more critical: - Does EP really overestimate the posterior variance? EP should overestimate the *support* of distributions, because the forward-KL covers all modes with a (unimodal) Gaussian. But this does not necessarily imply that the variance is overestimated, and locally the variance is matched exactly.