Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This theoretical paper derives low bounds on the number of samples needed to learn graphs (and not factors) from data. The paper uses various versions of the Fano lemma, e.g. Derivations and arguments are purely information-theoretic. The results are probably correct (I did not check the algebra), however I am not sure about the value of what is reported.