中文
相关论文

相关论文: Covariance loss, Szemeredi regularity, and differe…

200 篇论文

The protection of private information is of vital importance in data-driven research, business, and government. The conflict between privacy and utility has triggered intensive research in the computer science and statistics communities,…

密码学与安全 · 计算机科学 2022-08-11 March Boedihardjo , Thomas Strohmer , Roman Vershynin

We prove new lower bounds for statistical estimation tasks under the constraint of $(\varepsilon, \delta)$-differential privacy. First, we provide tight lower bounds for private covariance estimation of Gaussian distributions. We show that…

数据结构与算法 · 计算机科学 2023-03-29 Gautam Kamath , Argyris Mouzakis , Vikrant Singhal

We prove lower bounds on the number of samples needed to privately estimate the covariance matrix of a Gaussian distribution. Our bounds match existing upper bounds in the widest known setting of parameters. Our analysis relies on the…

数据结构与算法 · 计算机科学 2024-04-30 Victor S. Portella , Nick Harvey

In this paper, we present two new algorithms for covariance estimation under concentrated differential privacy (zCDP). The first algorithm achieves a Frobenius error of $\tilde{O}(d^{1/4}\sqrt{\mathrm{tr}}/\sqrt{n} + \sqrt{d}/n)$, where…

密码学与安全 · 计算机科学 2022-09-29 Wei Dong , Yuting Liang , Ke Yi

With changes in privacy laws, there is often a hard requirement for client data to remain on the device rather than being sent to the server. Therefore, most processing happens on the device, and only an altered element is sent to the…

密码学与安全 · 计算机科学 2022-12-27 Ajinkya K Mulay

We consider differentially private approximate singular vector computation. Known worst-case lower bounds show that the error of any differentially private algorithm must scale polynomially with the dimension of the singular vector. We are…

数据结构与算法 · 计算机科学 2012-11-06 Moritz Hardt , Aaron Roth

The conventional rounding error analysis provides worst-case bounds with an associated failure probability and ignores the statistical property of the rounding errors. In this paper, we develop a new statistical rounding error analysis for…

数值分析 · 数学 2025-11-04 Yiming Fang , Li Chen

Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the…

密码学与安全 · 计算机科学 2022-07-25 Elbert Du , Cynthia Dwork

We provide optimal lower bounds for two well-known parameter estimation (also known as statistical estimation) tasks in high dimensions with approximate differential privacy. First, we prove that for any $\alpha \le O(1)$, estimating the…

统计理论 · 数学 2024-01-05 Shyam Narayanan

Differential privacy (DP) is a mathematical framework that guarantees individual privacy; however, systematic evaluation of its impact on statistical utility in survival analyses remains limited. In this study, we systematically evaluated…

密码学与安全 · 计算机科学 2026-04-24 Keita Fukuyama , Yukiko Mori , Tomohiro Kuroda , Hiroaki Kikuchi

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples. In this paper, we focus on the privacy of pairwise…

机器学习 · 计算机科学 2021-06-02 Yilin Kang , Yong Liu , Jian Li , Weiping Wang

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve…

机器学习 · 计算机科学 2018-02-15 Di Wang , Minwei Ye , Jinhui Xu

Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. While differential privacy has emerged as a de facto standard for guaranteeing privacy in data sharing, the known mechanisms to…

密码学与安全 · 计算机科学 2024-03-26 March Boedihardjo , Thomas Strohmer , Roman Vershynin

We study the statistical complexity of private linear regression under an unknown, potentially ill-conditioned covariate distribution. Somewhat surprisingly, under privacy constraints the intrinsic complexity is \emph{not} captured by the…

机器学习 · 计算机科学 2025-11-06 Fan Chen , Jiachun Li , Alexander Rakhlin , David Simchi-Levi

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

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

机器学习 · 统计学 2022-10-18 Jiayuan Ye , Reza Shokri

This work is concerned with finite range bounds on the variance of individual eigenvalues of Wigner random matrices, in the bulk and at the edge of the spectrum, as well as for some intermediate eigenvalues. Relying on the GUE example,…

概率论 · 数学 2012-07-06 Sandrine Dallaporta

Kernel methods are successful approaches for different machine learning problems. This success is mainly rooted in using feature maps and kernel matrices. Some methods rely on the eigenvalues/eigenvectors of the kernel matrix, while for…

机器学习 · 计算机科学 2012-02-20 Nima Reyhani , Hideitsu Hino , Ricardo Vigario

In this paper, we study the problem of estimating the covariance matrix under differential privacy, where the underlying covariance matrix is assumed to be sparse and of high dimensions. We propose a new method, called DP-Thresholding, to…

机器学习 · 计算机科学 2019-04-17 Di Wang , Jinhui Xu

The increasing prevalence of high-dimensional data across various applications has raised significant privacy concerns in statistical inference. In this paper, we propose a differentially private integrated statistic for testing…

统计方法学 · 统计学 2025-06-04 Shiwei Sang , Yicheng Zeng , Xuehu Zhu , Shurong Zheng
‹ 上一页 1 2 3 10 下一页 ›