paper-with-me

홈 › Papers

Near-optimal algorithms for private estimation and sequential testing of collision probability

2025-04-18 · Robert Busa-Fekete, Umar Syed

We present new algorithms for estimating and testing \emph{collision probability}, a fundamental measure of the spread of a discrete distribution that is widely used in many scientific fields. We describe an algorithm that satisfies $(\alpha, \beta)$-local differential privacy and estimates collision probability with error at most $\epsilon$ using $\tilde{O}\left(\frac{\log(1/\beta)}{\alpha^2 \epsilon^2}\right)$ samples for $\alpha \le 1$, which improves over previous work by a factor of $\frac{1}{\alpha^2}$. We also present a sequential testing algorithm for collision probability, which can distinguish between collision probability values that are separated by $\epsilon$ using $\tilde{O}(\frac{1}{\epsilon^2})$ samples, even when $\epsilon$ is unknown. Our algorithms have nearly the optimal sample complexity, and in experiments we show that they require significantly fewer samples than previous methods.

📄 PDF Abstract BibTeX arXiv:2504.13804

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Fast Optimal Locally Private Mean Estimation via Random Projections

2023-06-07 · NeurIPS 2023 11 · Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen 외

We study the problem of locally private mean estimation of high-dimensional vectors in the Euclidean ball. Existing algorithms for this problem either incur sub-optimal error or have high communication and/or run-time co…

Federated Learning

Robustness Implies Privacy in Statistical Estimation

2022-12-09 · Samuel B. Hopkins, Gautam Kamath, Mahbod Majid, Shyam Narayanan

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private est…

Adversarial Robustnessparameter estimation

Instance-Optimal Differentially Private Estimation

2022-10-28 · Audra McMillan, Adam Smith, Jon Ullman

In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to …

From Robustness to Privacy and Back

2023-02-03 · Hilal Asi, Jonathan Ullman, Lydia Zakynthinou

We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. Their conceptual similarity was first obs…

On Differentially Private U Statistics

2024-07-06 · Kamalika Chaudhuri, Po-Ling Loh, Shourya Pandey, Purnamrita Sarkar

We consider the problem of privately estimating a parameter $\mathbb{E}[h(X_1,\dots,X_k)]$, where $X_1$, $X_2$, $\dots$, $X_k$ are i.i.d. data from some distribution and $h$ is a permutation-invariant function. Without p…