NeurIPS 2020

Breaking the Communication-Privacy-Accuracy Trilemma

Meta Review

This paper studies several basic statistical estimation problems in a distributed setting subject to local differential privacy constraint. The reviewers agree that the results presented in the paper shed new light on the trade-off between privacy, accuracy, and communication. In particular, the paper provides results for a wider range of privacy loss regimes (epsilon). The reviewers reached consensus that this paper should be accepted.