NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:387
Title:Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression


		
The paper addresses the problem of predicting the outcome of an action chosen from a set of possible actions with Distributionally Robust Nearest-Neighbor Regression. Additionally to the description of the method and its theoretical analysis, an application to finding optimal prescriptions for patients with hypertension is studied. The reviewers found that the paper was written in a clear manner. The ideas of the paper were found interesting and novel. The work brings a non trivial theoretical analysis. Some concerns were raised about 1), the benefit of using k-NN instead of sole Distributionally Robust Linear Regression 2), assumptions in the theoretical analysis and 3), the lack of discussion with a seemingly related literature in metric regression. The rebuttal satisfied most of the objections -- the authors are strongly encouraged to follow through, including the additional literature review they agreed to include. Assuming these are implemented as stated, this paper will be suitable for publication. This meta-review was reviewed and revised by the Program Chairs, based on discussions with the Senior Area Chair.