Review for NeurIPS paper: Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models

This paper presents a novel method for using undirected graphical models to perform inference on arbitrarily chosen subsets of random variables. Initial reviews all identified this as a novel and significant idea, but also raised several issues, mostly pertaining to the experimental validation. After author response and discussion, the reviewers feel these concerns were sufficiently addressed to recommend accepting this paper.