Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems
Abstract
We study the sample complexity of differentially private optimization of quasi-concave functions. For a fixed input domain , Cohen et al. (STOC 2023) proved that any generic private optimizer for low sensitive quasi-concave functions must have sample complexity . We show that the lower bound can be bypassed for a series of ``natural'' problems. We define a new class of \emph{approximated} quasi-concave functions, and present a generic differentially private optimizer for approximated quasi-concave functions with sample complexity . As applications, we use our optimizer to privately select a center point of points in dimensions and \emph{probably approximately correct} (PAC) learn -dimensional halfspaces. In previous works, Bun et al. (FOCS 2015) proved a lower bound of for both problems. Beimel et al. (COLT 2019) and Kaplan et al. (NeurIPS 2020) gave an upper bound of for the two problems, respectively. We improve the dependency of the upper bounds on the cardinality of the domain by presenting a new upper bound of for both problems. To the best of our understanding, this is the first work to reduce the sample complexity dependency on for these two problems from exponential in to .
Cite
@article{arxiv.2504.19001,
title = {Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems},
author = {Kobbi Nissim and Eliad Tsfadia and Chao Yan},
journal= {arXiv preprint arXiv:2504.19001},
year = {2025}
}