中文
相关论文

相关论文: Minimax optimal goodness-of-fit testing for densit…

200 篇论文

In the field of machine learning, many problems can be formulated as the minimax problem, including reinforcement learning, generative adversarial networks, to just name a few. So the minimax problem has attracted a huge amount of…

机器学习 · 计算机科学 2022-04-25 Yilin Kang , Yong Liu , Jian Li , Weiping Wang

We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance optimal: the former hold for the set of distribution pairs…

统计理论 · 数学 2023-12-19 Ankit Pensia , Amir R. Asadi , Varun Jog , Po-Ling Loh

We investigate the problems of identity and closeness testing over a discrete population from random samples. Our goal is to develop efficient testers while guaranteeing Differential Privacy to the individuals of the population. We describe…

机器学习 · 计算机科学 2017-07-19 Maryam Aliakbarpour , Ilias Diakonikolas , Ronitt Rubinfeld

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample…

统计理论 · 数学 2019-12-11 Thomas Berrett , Cristina Butucea

We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. The commonly adopted compression schemes introduce…

密码学与安全 · 计算机科学 2024-02-02 Richeng Jin , Zhonggen Su , Caijun Zhong , Zhaoyang Zhang , Tony Quek , Huaiyu Dai

A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a data-dependent function, all under the constraint of…

机器学习 · 计算机科学 2014-09-09 Kamalika Chaudhuri , Daniel Hsu , Shuang Song

Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…

机器学习 · 计算机科学 2017-06-01 Katrina Ligett , Seth Neel , Aaron Roth , Bo Waggoner , Z. Steven Wu

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…

数据结构与算法 · 计算机科学 2022-03-07 Clément L. Canonne , Gautam Kamath , Audra McMillan , Jonathan Ullman , Lydia Zakynthinou

We initiate the study of distribution testing under \emph{user-level} local differential privacy, where each of $n$ users contributes $m$ samples from the unknown underlying distribution. This setting, albeit very natural, is significantly…

数据结构与算法 · 计算机科学 2025-10-22 Clément L. Canonne , Abigail Gentle , Vikrant Singhal

Through the lens of information-theoretic reductions, we examine a reductions approach to fair optimization and learning where a black-box optimizer is used to learn a fair model for classification or regression. Quantifying the complexity,…

机器学习 · 计算机科学 2021-05-25 Daniel Alabi

In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involved individuals. This is achieved by randomly perturbing the…

密码学与安全 · 计算机科学 2024-12-18 Aras Selvi , Huikang Liu , Wolfram Wiesemann

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

机器学习 · 统计学 2019-06-04 Abhishek Bhowmick , John Duchi , Julien Freudiger , Gaurav Kapoor , Ryan Rogers

This paper considers minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. Our study is conducted within a heterogeneous framework,…

统计理论 · 数学 2024-07-01 Arnab Auddy , T. Tony Cai , Abhinav Chakraborty

Although robust learning and local differential privacy are both widely studied fields of research, combining the two settings is just starting to be explored. We consider the problem of estimating a discrete distribution in total variation…

统计理论 · 数学 2022-04-21 Julien Chhor , Flore Sentenac

The covariance matrix plays a fundamental role in the analysis of high-dimensional data. This paper studies minimax and adaptive estimation of high-dimensional bandable covariance matrices under differential privacy constraints. We propose…

统计理论 · 数学 2026-03-23 T. Tony Cai , Yicheng Li

Privacy-protecting data analysis investigates statistical methods under privacy constraints. This is a rising challenge in modern statistics, as the achievement of confidentiality guarantees, which typically occurs through suitable…

统计理论 · 数学 2022-09-14 Emanuele Dolera , Stefano Favaro

We study the problem of mean estimation of $\ell_2$-bounded vectors under the constraint of local differential privacy. While the literature has a variety of algorithms that achieve the asymptotically optimal rates for this problem, the…

机器学习 · 计算机科学 2022-05-06 Hilal Asi , Vitaly Feldman , Kunal Talwar

Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional DP formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world…

密码学与安全 · 计算机科学 2023-05-18 Syomantak Chaudhuri , Thomas A. Courtade

In this paper, we initiate a systematic investigation of differentially private algorithms for convex empirical risk minimization. Various instantiations of this problem have been studied before. We provide new algorithms and matching lower…

机器学习 · 计算机科学 2014-10-21 Raef Bassily , Adam Smith , Abhradeep Thakurta

We study the fundamental task of estimating the median of an underlying distribution from a finite number of samples, under pure differential privacy constraints. We focus on distributions satisfying the minimal assumption that they have a…