NeurIPS 2020

Privacy Amplification via Random Check-Ins

Meta Review

This paper provides a new privacy amplification technique for differential privacy. The proposed solution is a novel contribution to the literature. During the reviewer discussion, there were concerns that the method is not fully practical and yet the main motivation of the paper is that the previous techniques may not work in practice when the data are distributed across different nodes. The authors should provide an honest discussion of these practical issues raised in the reviews.