Reviews: Differential Privacy Has Disparate Impact on Model Accuracy

Overall I have only listed one contribution, but I consider this contribution to be very significant. In general, I consider this to be a high quality submission on the basis of the finding and thoroughness of the experiments. My only qualms would be addition clarity in explaining results and contextualizing these results in light of recent work. Originality I consider this finding to be inline with come previous work, in particular, citation 20 in the paper. However, this is the first work that demonstrates, empirically, and in a convincing fashion that tradeoffs between privacy and minority impact.