2024-06-30-ghazi24a.md

title	section	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
On Convex Optimization with Semi-Sensitive Features	Original Papers	We study the differentially private (DP) empirical risk minimization (ERM) problem under the \emph{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 size of the sensitive domain (Ghazi et al., NeurIPS 2021).	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	ghazi24a	0	On Convex Optimization with Semi-Sensitive Features	1916	1938	1916-1938	1916	false	Ghazi, Badih and Kamath, Pritish and Kumar, Ravi and Manurangsi, Pasin and Meka, Raghu and Zhang, Chiyuan	given family Badih Ghazi given family Pritish Kamath given family Ravi Kumar given family Pasin Manurangsi given family Raghu Meka given family Chiyuan Zhang	2024-06-30		Proceedings of Thirty Seventh Conference on Learning Theory	247	inproceedings	date-parts 2024 6 30	https://proceedings.mlr.press/v247/ghazi24a/ghazi24a.pdf