# On Convex Optimization with Semi-Sensitive Features

arXiv: https://arxiv.org/abs/2406.19040 · HTML: https://mlsanity.com/paper/2406.19040/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [Private Stochastic Convex Optimization with Optimal Rates](https://mlsanity.com/paper/1908.09970/) (2019)
- [Private Stochastic Convex Optimization: Optimal Rates in Linear Time](https://mlsanity.com/paper/2005.04763/) (2020)
- [Concentrated Differential Privacy](https://mlsanity.com/paper/1603.01887/) (2016)
- [Differentially Private Empirical Risk Minimization Revisited: Faster and More General](https://mlsanity.com/paper/1802.05251/) (2018)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Private Convex Optimization via Exponential Mechanism](https://mlsanity.com/paper/2203.00263/) (2022)
- [Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization](https://mlsanity.com/paper/1512.09170/) (2015)
- [Private Multiplicative Weights Beyond Linear Queries](https://mlsanity.com/paper/1407.1571/) (2014)
- [Regression with Label Differential Privacy](https://mlsanity.com/paper/2212.06074/) (2022)
- [Private Learning with Public Features](https://mlsanity.com/paper/2310.15454/) (2023)
- [Training Differentially Private Ad Prediction Models with Semi-Sensitive Features](https://mlsanity.com/paper/2401.15246/) (2024)
- [Classification with Partially Private Features](https://mlsanity.com/paper/2312.07583/) (2023)

## Built on by (most cited first, 1 of 1)

- [Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM](https://mlsanity.com/paper/2605.03945/) (2026)

## 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).