no code implementations • 9 Feb 2024 • Eliad Tsfadia
If the low-dimensional structure could be privately identified using a small amount of points, we could avoid paying (in terms of privacy and accuracy) for the high ambient dimension.
no code implementations • 14 Jul 2023 • Naty Peter, Eliad Tsfadia, Jonathan Ullman
Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error of approximately differentially private (DP) algorithms.
no code implementations • 29 Dec 2021 • Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
Clustering is a fundamental problem in data analysis.
no code implementations • 19 Oct 2021 • Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results.
no code implementations • NeurIPS 2020 • Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia
We present a differentially private learner for halfspaces over a finite grid $G$ in $\mathbb{R}^d$ with sample complexity $\approx d^{2. 5}\cdot 2^{\log^*|G|}$, which improves the state-of-the-art result of [Beimel et al., COLT 2019] by a $d^2$ factor.