DeepAI AI Chat
Log In Sign Up

Minimax optimal goodness-of-fit testing for densities under a local differential privacy constraint

by   Joseph Lam-Weil, et al.

Finding anonymization mechanisms to protect personal data is at the heart of machine learning research. Here we consider the consequences of local differential privacy constraints on goodness-of-fit testing, i.e. the statistical problem assessing whether sample points are generated from a fixed density f_0, or not. The observations are hidden and replaced by a stochastic transformation satisfying the local differential privacy constraint. In this setting, we propose a new testing procedure which is based on an estimation of the quadratic distance between the density f of the unobserved sample and f_0. We establish minimax separation rates for our test over Besov balls. We also provide a lower bound, proving the optimality of our result. To the best of our knowledge, we provide the first minimax optimal test and associated private transformation under a local differential privacy constraint, quantifying the price to pay for data privacy.


page 1

page 2

page 3

page 4


Goodness-of-fit testing for Hölder continuous densities under local differential privacy

We address the problem of goodness-of-fit testing for Hölder continuous ...

Robust Estimation of Discrete Distributions under Local Differential Privacy

Although robust learning and local differential privacy are both widely ...

On robustness and local differential privacy

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

Geometrizing rates of convergence under differential privacy constraints

We study estimation of a functional θ( P) of an unknown probability dist...

Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning

Achieving optimal statistical performance while ensuring the privacy of ...

Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

We find separation rates for testing multinomial or more general discret...

Efficiency in local differential privacy

We develop a theory of asymptotic efficiency in regular parametric model...