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

02/13/2018
by   Jayadev Acharya, et al.
0

We consider discrete distribution estimation over k elements under ε-local differential privacy from n samples. The samples are distributed across users who send privatized versions of their sample to the server. All previously known sample optimal algorithms require linear (in k) communication complexity in the high privacy regime (ε<1), and have a running time that grows as n· k, which can be prohibitive for large domain size k. We study the task simultaneously under four resource constraints, privacy, sample complexity, computational complexity, and communication complexity. We propose Hadamard Response (HR), a local non-interactive privatization mechanism with order optimal sample complexity (for all privacy regimes), a communication complexity of k+2 bits, and runs in nearly linear time. Our encoding and decoding mechanisms are based on Hadamard matrices, and are simple to implement. The gain in sample complexity comes from the large Hamming distance between rows of Hadamard matrices, and the gain in time complexity is achieved by using the Fast Walsh-Hadamard transform. We compare our approach with Randomized Response (RR), RAPPOR, and subset-selection mechanisms (SS), theoretically, and experimentally. For k=10000, our algorithm runs about 100x faster than SS, and RAPPOR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/03/2020

Compressive Privatization: Sparse Distribution Estimation under Locally Differentially Privacy

We consider the problem of discrete distribution estimation under locall...
research
05/12/2023

Private and Communication-Efficient Algorithms for Entropy Estimation

Modern statistical estimation is often performed in a distributed settin...
research
07/22/2020

Breaking the Communication-Privacy-Accuracy Trilemma

Two major challenges in distributed learning and estimation are 1) prese...
research
10/30/2020

Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints

We consider the task of estimating sparse discrete distributions under l...
research
11/19/2019

The Power of Factorization Mechanisms in Local and Central Differential Privacy

We give new characterizations of the sample complexity of answering line...
research
02/12/2018

Efficient Empirical Risk Minimization with Smooth Loss Functions in Non-interactive Local Differential Privacy

In this paper, we study the Empirical Risk Minimization problem in the n...
research
07/24/2021

On the Sample Complexity of Privately Learning Axis-Aligned Rectangles

We revisit the fundamental problem of learning Axis-Aligned-Rectangles o...

Please sign up or login with your details

Forgot password? Click here to reset