Differentially Private Selection from Secure Distributed Computing

ePrint Report: Differentially Private Selection from Secure Distributed Computing

Ivan Damgård, Hannah Keller, Boel Nelson, Claudio Orlandi, Rasmus Pagh

Given a collection of vectors $\mathbf{x}^{(1)},\dots,\mathbf{x}^{(n)} \in \{0,1\}^d$, the selection problem asks to report the index of an "approximately largest" entry in $\mathbf{x}=\sum_{j=1}^n \mathbf{x}^{(j)}$. Selection abstracts a host of problems; in machine learning it can be used for hyperparameter tuning, feature selection, or to model empirical risk minimization. We study selection under differential privacy, where a released index guarantees privacy for …

collection computing distributed distributed computing entry eprint report host machine machine learning private problem problems report