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

The paper proposes a new inference task for graphical models. It consists in finding a MAP assignment w.r.t. It contains as special cases several interesting graphical model problems like m-best assigments. The method uses a transformation to multiple choice knapsack for cmputationally solving the problem. Authors agree that the new problem is interesting and the transformation to multiple choice knapsack is interesting. The main criticism pertains to the small experiments that are not necessarily indicative of real-world problems.