REVIEW 4 cited by
Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning
read the original abstract
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 non-parametric regression over the Sobolev class.
Forward citations
Cited by 4 Pith papers
-
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
Derives a federated van Trees lower bound under total clientwise sample-level zCDP for parameter estimation with squared l2 loss in federated learning protocols with arbitrary public-transcript interactions.
-
Robust Statistical Estimators with Bounded Empirical Sensitivity
Defines empirical sensitivity and proves Ω(η + √(η d/n)) lower bound (tight up to logs) for any Gaussian mean estimator achieving optimal O(√(d/n)) ℓ₂ error.
-
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
Under clientwise sample-level zCDP, the Fisher information of any fully interactive public federated transcript contracts to a sum of per-client privacy-vs-sample terms, yielding matching minimax rates for mean, linea...
-
High-Dimensional Private Linear Regression with Optimal Rates
DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.