Review for NeurIPS paper: A Novel Approach for Constrained Optimization in Graphical Models

Additional Feedback: Major: - Why the SCIP solver was used as a baseline and not Gurobi? My experience suggests that Gurobi typically performs notably better and the academic license is free. It seems you unintentionally deleted a part of it. Minor: - I would suggest to use the term "volume" instead of "cost", as it makes more sense to restrict the volume and maximize the profit than to restrict the costs and maximize the profit, especially when one speaks about a knapsack (with a predefined volume). It becomes more readable, if you would write "m is the number of log-potentials, i.e. m \mathbf(f) ". x l argmax ..., x u argmin ... l155: the sentence "and a real number q such that no two functions ... share any variable..." - is ambiguous. Put "and a real number q" right before "we can construct" instead.