English
Related papers

Related papers: The Test of Tests: A Framework For Differentially …

200 papers

This paper introduces a novel theoretical framework for auditing differential privacy (DP) in a black-box setting. Leveraging the concept of $f$-differential privacy, we explicitly define type I and type II errors and propose an auditing…

Methodology · Statistics 2025-04-14 Kaining Shi , Cong Ma

Context: Differential testing is a useful approach that uses different implementations of the same algorithms and compares the results for software testing. In recent years, this approach was successfully used for test campaigns of deep…

Software Engineering · Computer Science 2022-07-26 Steffen Herbold , Steffen Tunkel

The maximum type-I and type-II error exponents associated with the newly introduced almost-fixed-length hypothesis testing is characterized. In this class of tests, the decision-maker declares the true hypothesis almost always after…

Information Theory · Computer Science 2016-05-18 Anusha Lalitha , Tara Javidi

We extend the framework of augmented distribution testing (Aliakbarpour, Indyk, Rubinfeld, and Silwal, NeurIPS 2024) to the differentially private setting. This captures scenarios where a data analyst must perform hypothesis testing tasks…

Machine Learning · Computer Science 2025-03-20 Maryam Aliakbarpour , Arnav Burudgunte , Clément Cannone , Ronitt Rubinfeld

Kernel-based tests provide a simple yet effective framework that use the theory of reproducing kernel Hilbert spaces to design non-parametric testing procedures. In this paper we propose new theoretical tools that can be used to study the…

Statistics Theory · Mathematics 2022-09-02 Tamara Fernández , Nicolás Rivera

In this work we present novel differentially private identity (goodness-of-fit) testers for natural and widely studied classes of multivariate product distributions: Gaussians in $\mathbb{R}^d$ with known covariance and product…

Data Structures and Algorithms · Computer Science 2022-03-07 Clément L. Canonne , Gautam Kamath , Audra McMillan , Jonathan Ullman , Lydia Zakynthinou

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many…

Machine Learning · Computer Science 2020-06-26 Lingjuan Lyu , Yitong Li , Xuanli He , Tong Xiao

We consider the problems of hypothesis testing on a probability measure of independent sample, on solution of ill-posed problem, on deconvolution problem and on Poisson mean measure. For all these setups necessary conditions and sufficient…

Statistics Theory · Mathematics 2013-10-24 Mikhail Ermakov

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Cryptography and Security · Computer Science 2024-12-17 Bo Jiang , Wanrong Zhang , Donghang Lu , Jian Du , Sagar Sharma , Qiang Yan

We study private two-terminal hypothesis testing with simple hypotheses where the privacy goal is to ensure that participating in the testing protocol reveals little additional information about the other user's observation when a user is…

Information Theory · Computer Science 2020-05-13 Varun Narayanan , Manoj Mishra , Vinod M. Prabhakaran

We provide a differentially private algorithm for hypothesis selection. Given samples from an unknown probability distribution $P$ and a set of $m$ probability distributions $\mathcal{H}$, the goal is to output, in a…

Data Structures and Algorithms · Computer Science 2021-01-05 Mark Bun , Gautam Kamath , Thomas Steinke , Zhiwei Steven Wu

In hypothesis testing problems the property of strict unbiasedness describes whether a test is able to discriminate, in the sense of a difference in power, between any distribution in the null hypothesis space and any distribution in the…

Statistics Theory · Mathematics 2025-06-11 Andrew McCormack

Confidence intervals for the population mean of normally distributed data are some of the most standard statistical outputs one might want from a database. In this work we give practical differentially private algorithms for this task. We…

Methodology · Statistics 2020-01-09 Wenxin Du , Canyon Foot , Monica Moniot , Andrew Bray , Adam Groce

We propose a scheme for auditing differentially private machine learning systems with a single training run. This exploits the parallelism of being able to add or remove multiple training examples independently. We analyze this using the…

Machine Learning · Computer Science 2023-05-16 Thomas Steinke , Milad Nasr , Matthew Jagielski

The purpose of this paper is to develop a mathematical analysis theory to solve differential privacy problems. The heart of our approaches is to use analytic tools to characterize the correlations among the outputs of different datasets,…

Cryptography and Security · Computer Science 2018-01-30 Genqiang Wu , Xianyao Xia , Yeping He

In differential privacy (DP), the generalized private testing problem was introduced by Liu and Talwar (STOC 2019). Given a dataset $X \in \mathcal{X}$ and a sequence of black-box $\varepsilon_t$-DP mechanisms $M_t:\mathcal{X}\to\{+1,-1\}$,…

Data Structures and Algorithms · Computer Science 2026-05-22 Anamay Chaturvedi , Monika Henzinger , Jalaj Upadhyay

Modern society generates an incredible amount of data about individuals, and releasing summary statistics about this data in a manner that provably protects individual privacy would offer a valuable resource for researchers in many fields.…

Cryptography and Security · Computer Science 2018-02-21 Zachary Campbell , Andrew Bray , Anna Ritz , Adam Groce

The increasing usage of machine learning models raises the question of the reliability of these models. The current practice of testing with limited data is often insufficient. In this paper, we provide a framework for automated test data…

Machine Learning · Computer Science 2021-11-04 Diptikalyan Saha , Aniya Aggarwal , Sandeep Hans

A hypothesis testing algorithm is replicable if, when run on two different samples from the same distribution, it produces the same output with high probability. This notion, defined by by Impagliazzo, Lei, Pitassi, and Sorell [STOC'22],…

Data Structures and Algorithms · Computer Science 2025-09-05 Anders Aamand , Maryam Aliakbarpour , Justin Y. Chen , Shyam Narayanan , Sandeep Silwal

In this paper, we present a general framework for testing relevant hypotheses in functional time series. Our unified approach covers one-sample, two-sample, and change point problems under contaminated observations with arbitrary sampling…

Methodology · Statistics 2025-08-27 Leheng Cai , Qirui Hu
‹ Prev 1 3 4 5 6 7 10 Next ›