Differentially Private Clustering: Tight Approximation Ratios

08/18/2020
by   Badih Ghazi, et al.
1

We study the task of differentially private clustering. For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, we give efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors. This improves upon existing efficient algorithms that only achieve some large constant approximation factors. Our results also imply an improved algorithm for the Sample and Aggregate privacy framework. Furthermore, we show that one of the tools used in our 1-Cluster algorithm can be employed to get a faster quantum algorithm for ClosestPair in a moderate number of dimensions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/28/2020

A note on differentially private clustering with large additive error

In this note, we describe a simple approach to obtain a differentially p...
research
04/27/2023

Improving the Utility of Differentially Private Clustering through Dynamical Processing

This study aims to alleviate the trade-off between utility and privacy i...
research
02/17/2021

Differentially Private Correlation Clustering

Correlation clustering is a widely used technique in unsupervised machin...
research
02/08/2019

Achieving Data Utility-Privacy Tradeoff in Internet of Medical Things: A Machine Learning Approach

The emergence and rapid development of the Internet of Medical Things (I...
research
06/17/2022

Scalable Differentially Private Clustering via Hierarchically Separated Trees

We study the private k-median and k-means clustering problem in d dimens...
research
07/06/2022

Private Matrix Approximation and Geometry of Unitary Orbits

Consider the following optimization problem: Given n × n matrices A and ...
research
01/31/2023

Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees

Hierarchical Clustering is a popular unsupervised machine learning metho...

Please sign up or login with your details

Forgot password? Click here to reset