LGCRDSJun 27, 2024

On Convex Optimization with Semi-Sensitive Features

arXiv:2406.19040v12 citations
Originality Incremental advance
AI Analysis

This addresses privacy-preserving machine learning for scenarios with mixed sensitive and non-sensitive features, representing an incremental advance over prior work.

The paper tackles differentially private empirical risk minimization when only some features are sensitive, showing that error scales polylogarithmically with sensitive domain size, improving upon previous polynomial scaling.

We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved upper and lower bounds on the excess risk for DP-ERM. In particular, we show that the error only scales polylogarithmically in terms of the sensitive domain size, improving upon previous results that scale polynomially in the sensitive domain size (Ghazi et al., 2021).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes