Prior-Aware Distribution Estimation for Differential Privacy

by   Yuchao Tao, et al.

Joint distribution estimation of a dataset under differential privacy is a fundamental problem for many privacy-focused applications, such as query answering, machine learning tasks and synthetic data generation. In this work, we examine the joint distribution estimation problem given two data points: 1) differentially private answers of a workload computed over private data and 2) a prior empirical distribution from a public dataset. Our goal is to find a new distribution such that estimating the workload using this distribution is as accurate as the differentially private answer, and the relative entropy, or KL divergence, of this distribution is minimized with respect to the prior distribution. We propose an approach based on iterative optimization for solving this problem. An application of our solution won second place in the NIST 2020 Differential Privacy Temporal Map Challenge, Sprint 2.



There are no comments yet.


page 1

page 2

page 3

page 4


Auditing Differentially Private Machine Learning: How Private is Private SGD?

We investigate whether Differentially Private SGD offers better privacy ...

A New Analysis of Differential Privacy's Generalization Guarantees

We give a new proof of the "transfer theorem" underlying adaptive data a...

A Differentially Private Algorithm for Range Queries on Trajectories

We propose a novel algorithm to ensure ϵ-differential privacy for answer...

Differentially Private n-gram Extraction

We revisit the problem of n-gram extraction in the differential privacy ...

INSPECTRE: Privately Estimating the Unseen

We develop differentially private methods for estimating various distrib...

Differentially Private Distributed Data Summarization under Covariate Shift

We envision AI marketplaces to be platforms where consumers, with very l...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.