Reviews: Structure Learning with Side Information: Sample Complexity

This paper studies the problem of "simultaneously learning two Ising models whose underlying graphs have some similarity constraints." The problem is interesting (and well-motivated) and the authors provide matching upper and lower bounds, with sharper characterization in some regimes. The proofs use more or less standard approaches, although applying these requires nontrivial work. Overall this is a solid contribution to NeurIPS. The authors responded to most of the reviewer's concerns.