Log In Sign Up

Breaking the Communication-Privacy-Accuracy Trilemma

by   Wei-Ning Chen, et al.

Two major challenges in distributed learning and estimation are 1) preserving the privacy of the local samples; and 2) communicating them efficiently to a central server, while achieving high accuracy for the end-to-end task. While there has been significant interest in addressing each of these challenges separately in the recent literature, treatments that simultaneously address both challenges are still largely missing. In this paper, we develop novel encoding and decoding mechanisms that simultaneously achieve optimal privacy and communication efficiency in various canonical settings. In particular, we consider the problems of mean estimation and frequency estimation under ε-local differential privacy and b-bit communication constraints. For mean estimation, we propose a scheme based on Kashin's representation and random sampling, with order-optimal estimation error under both constraints. For frequency estimation, we present a mechanism that leverages the recursive structure of Walsh-Hadamard matrices and achieves order-optimal estimation error for all privacy levels and communication budgets. As a by-product, we also construct a distribution estimation mechanism that is rate-optimal for all privacy regimes and communication constraints, extending recent work that is limited to b=1 and ε=O(1). Our results demonstrate that intelligent encoding under joint privacy and communication constraints can yield a performance that matches the optimal accuracy achievable under either constraint alone.


page 1

page 2

page 3

page 4


Communication Efficient, Sample Optimal, Linear Time Locally Private Discrete Distribution Estimation

We consider discrete distribution estimation over k elements under ε-loc...

A normal approximation for joint frequency estimatation under Local Differential Privacy

In the recent years, Local Differential Privacy (LDP) has been one of th...

Frequency Estimation Under Multiparty Differential Privacy: One-shot and Streaming

We study the fundamental problem of frequency estimation under both priv...

Discrete Distribution Estimation under User-level Local Differential Privacy

We study discrete distribution estimation under user-level local differe...

Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters

We consider the problems of distribution estimation and heavy hitter (fr...

On robustness and local differential privacy

It is of soaring demand to develop statistical analysis tools that are r...

Communication-Efficient Triangle Counting under Local Differential Privacy

Triangle counting in networks under LDP (Local Differential Privacy) is ...