DeepAI AI Chat
Log In Sign Up

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

by   T. Tony Cai, et al.

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.


page 1

page 2

page 3

page 4


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...

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

We propose differentially private algorithms for parameter estimation in...

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...

On rate optimal private regression under local differential privacy

We consider the problem of estimating a regression function from anonymi...

On robustness and local differential privacy

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

Minimax Rates of Estimating Approximate Differential Privacy

Differential privacy has become a widely accepted notion of privacy, lea...

Fundamental Tradeoffs in Learning with Prior Information

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