Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
The authors study a new block coordinate descent algorithm for the sparse group lasso. The contributions appear solid and the reviewers were mostly positive about the work. I would like the authors to pay close attention to the points raised by Reviewer 3 about the theory and to revise the paper so that this is made more clear to the reader. Also, if the proposed algorithm applies to the overlap case (a very important case in general) then this should also be made clear.