Review for NeurIPS paper: An efficient nonconvex reformulation of stagewise convex optimization problems

Neural Information Processing Systems 

Additional Feedback: Update after rebuttal After reading the rebuttal, I am happy with the answers regarding PDHG, and explanations about the proof for backtracking/momentum variants of the method. I find the approach promising. However, I think the work needs improvements in terms of presentation, which, I suggest the authors to consider when revising the paper. Especially the introduction of the idea can be made more friendly for the readers, with more explanations. I suggest the authors to also consider the minor questions in my review that are not mentioned in the rebuttal.