Review for NeurIPS paper: Fairness without Demographics through Adversarially Reweighted Learning

Additional Feedback: It would be help to provide more explanation of the figures in the captions --e.g. It would be helpful early on to give some intuition about what are computationally identifiable groups; this only became clear to me after reading a few pages. It would also be helpful to give a definition environment when you formally define this on lines 180-181. Line 172 -- specifying that the weights are over S would be helpful. In Equation 5, what does the subscript "ce" mean?