DeepAI AI Chat
Log In Sign Up

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

03/13/2023
by   T. Tony Cai, et al.
0

Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However, characterizing the optimality, particularly the minimax lower bound, under privacy constraints is technically difficult. To address this issue, we propose a novel approach called the score attack, which provides a lower bound on the differential-privacy-constrained minimax risk of parameter estimation. The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a well-defined score statistic. It can optimally lower bound the minimax risk of estimating unknown model parameters, up to a logarithmic factor, while ensuring differential privacy for a range of statistical problems. We demonstrate the effectiveness and optimality of this general method in various examples, such as the generalized linear model in both classical and high-dimensional sparse settings, the Bradley-Terry-Luce model for pairwise comparisons, and nonparametric regression over the Sobolev class.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/12/2019

The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy

Privacy-preserving data analysis is a rising challenge in contemporary s...
11/08/2020

The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds

We propose differentially private algorithms for parameter estimation in...
02/11/2020

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

Finding anonymization mechanisms to protect personal data is at the hear...
05/31/2022

On rate optimal private regression under local differential privacy

We consider the problem of estimating a regression function from anonymi...
01/03/2022

On robustness and local differential privacy

It is of soaring demand to develop statistical analysis tools that are r...
05/24/2019

Minimax Rates of Estimating Approximate Differential Privacy

Differential privacy has become a widely accepted notion of privacy, lea...
04/26/2023

Fundamental Tradeoffs in Learning with Prior Information

We seek to understand fundamental tradeoffs between the accuracy of prio...