On Convex Optimization with Semi-Sensitive Features
Not on the map. Why?
Abstract (arXiv)
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).
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 27 Jun 2024.
Builds on
13 of 25 references.
References · 13
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
- 2019Private Stochastic Convex Optimization with Optimal Ratescited by 183
- 2020Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 152
- 2016Concentrated Differential Privacycited by 139
- 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 127
- 2021Deep Learning with Label Differential Privacycited by 113
- 2022Private Convex Optimization via Exponential Mechanismcited by 47
- 2015Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimizationcited by 41
- 2014Private Multiplicative Weights Beyond Linear Queriescited by 17
- 2022Regression with Label Differential Privacycited by 14
- 2023Private Learning with Public Featurescited by 6
- 2024Training Differentially Private Ad Prediction Models with Semi-Sensitive Featurescited by 6
1 more
- 2023Classification with Partially Private Featurescited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.