Fabrizio Boninsegna
LightNews LightNews
nynsenfaber.bsky.social
Fabrizio Boninsegna
@nynsenfaber.bsky.social
15 followers 12 following 0 posts
PhD student in differential privacy and mobility at the University of Padova. Master's in Theoretical Physics.
Love long hiking and music.
Posts Replies Media Videos
Reposted by Fabrizio Boninsegna
dppapers.bsky.social
Differentially Private Quantiles with Smaller Error

Jacob Imola, Fabrizio Boninsegna, Hannah Keller, Anders Aamand, Amrita Roy Chowdhury, Rasmus Pagh

http://arxiv.org/abs/2505.13662
Differentially Private Quantiles with Smaller Error Jacob Imola, Fabrizio Boninsegna, Hannah Keller, Anders Aamand, Amrita Roy Chowdhury, Rasmus Pagh http://arxiv.org/abs/2505.13662 In the approximate quantiles problem, the goal is to output $m$ quantile estimates, the ranks of which are as close as possible to $m$ given quantiles $q_1,\dots,q_m$. We present a mechanism for approximate quantiles that satisfies $\varepsilon$-differential privacy for a dataset of $n$ real numbers where the ratio between the closest pair of points and the size of the domain is bounded by $b$. As long as the minimum gap between quantiles is large enough, $|q_i-q_{i-1}|\geq \Omega\left(\frac{m\log(m)\log(b)}{n\varepsilon}\right)$ for all $i$, the maximum rank error of our mechanism is $O\left(\frac{\log(b) + \log^2(m)}{\varepsilon}\right)$ with high probability. Previously, the best known algorithm under pure DP was due to Kaplan, Schnapp, and Stemmer~(ICML '22), who achieve a bound of $O\left(\log(b)\log^2(m)/\varepsilon\right)$, so we save a factor $\Omega(\min(\log(b),\log^2(m)))$. Our improvement stems from the use of continual counting techniques to randomize the quantiles in a correlated way. We also present an $(\varepsilon,\delta)$-differentially private mechanism that relaxes the gap assumption without affecting the error bound, improving on existing methods when $\delta$ is sufficiently close to zero. We provide experimental evaluation which confirms that our mechanism performs favorably compared to prior work in practice, in particular when the number of quantiles $m$ is large.
May 21, 2025 at 3:48 AM
Reposted by Fabrizio Boninsegna
ccanonne.github.io
This is joint work of hers with Anders Aamand, Fabrizio Boninsegna (@nynsenfaber.bsky.social), Jacob Imola, and Rasmus Pagh (@rasmuspagh.net), and shows how adaptivity helps for private distributed median (more generally, quantile) estimation, reducing the data requirements.
arxiv.org/abs/2502.02990
Lightweight Protocols for Distributed Private Quantile Estimation
Distributed data analysis is a large and growing field driven by a massive proliferation of user devices, and by privacy concerns surrounding the centralised storage of data. We consider two \emph{ada...
arxiv.org
May 1, 2025 at 9:03 PM