Reviews: GILBO: One Metric to Measure Them All

Overall I think is a very good paper and it is one of the better papers I've seen addressing evaluating GANs. I myself are fairly skeptical of FID and have seen other works criticizing that approach, and this work sheds some light on the situation. I think anyone who follows this work would be better informed than work that introduced inception or FID in how to evaluate GANs. That said, there is some missing discussion or comparison to related work (notably mutual information neural estimation (MINE) by Belghazi et al, 2018) as well as some discussion related to the inductive bias and boundedness of their estimator. I'd like to see a discussion of these things.