Review for NeurIPS paper: Fairness constraints can help exact inference in structured prediction

My biggest concern is with the way that \epsilon_1 behaves depending on n. Firstly, it seems the choice of the value -n for \rho is arbitrary (with the choice being repercuted in the definition of \epsilon), and this should be discussed more clearly in the text. Next, it is not clear to me why the choice \rho -n is the best. Does it optimize \epsilon_1 in some way? Furthermore, as n tends to \infty, it seems that \epsilon_1 does NOT tend to infinity.