NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:5810
Title:Superposition of many models into one

The reviewers did not come to a consensus on the merits of this paper. In my opinion, the approach presented is novel and interesting; but I share R1's concerns about the discussion of earlier work and lack of empirical comparisons. I am recommending the paper be accepted, but the authors should include a discussion of these prior works, and comparisons to relevant methods where appropriate.