English
Related papers

Related papers: On Differentially Private Subspace Estimation in a…

200 papers

It is well known that non-parametric methods suffer from the "curse of dimensionality". We propose here a new estimation method for a multivariate distribution, using sub-sampling and ranks, which seems not to suffer from this "curse". We…

Statistics Theory · Mathematics 2013-11-08 Collet Jérôme

Dimension reduction is often an important step in the analysis of high-dimensional data. PCA is a popular technique to find the best low-dimensional approximation of high-dimensional data. However, classical PCA is very sensitive to…

Computation · Statistics 2019-01-14 Holger Cevallos-Valdiviezo , Stefan Van Aelst

The simplest and most widely applied method for guaranteeing differential privacy is to add instance-independent noise to a statistic of interest that is scaled to its global sensitivity. However, global sensitivity is a worst-case notion…

Statistics Theory · Mathematics 2019-06-10 Mark Bun , Thomas Steinke

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…

Methodology · Statistics 2025-06-04 Shiwei Sang , Yicheng Zeng , Xuehu Zhu , Shurong Zheng

Derivative-free algorithms seek the minimum of a given function based only on function values queried at appropriate points. Although these methods are widely used in practice, their performance is known to worsen as the problem dimension…

Optimization and Control · Mathematics 2023-08-10 Warren Hare , Lindon Roberts , Clément W. Royer

Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their…

Statistics Theory · Mathematics 2024-10-10 Gautam Kamath , Argyris Mouzakis , Matthew Regehr , Vikrant Singhal , Thomas Steinke , Jonathan Ullman

Common datasets have the form of elements with keys (e.g., transactions and products) and the goal is to perform analytics on the aggregated form of key and frequency pairs. A weighted sample of keys by (a function of) frequency is a highly…

Machine Learning · Computer Science 2021-04-01 Edith Cohen , Ofir Geri , Tamas Sarlos , Uri Stemmer

We present a high-dimensional analysis of three popular algorithms, namely, Oja's method, GROUSE and PETRELS, for subspace estimation from streaming and highly incomplete observations. We show that, with proper time scaling, the…

Machine Learning · Computer Science 2019-01-30 Chuang Wang , Yonina C. Eldar , Yue M. Lu

Statistical data depth plays an important role in the analysis of multivariate data sets. The main outcome is a center-outward ordering of the observations that can be used both to highlight features of the underlying distribution of the…

Statistics Theory · Mathematics 2026-03-11 Giacomo Francisci , Claudio Agostinelli

We propose a novel and computationally efficient approach for nonparametric conditional density estimation in high-dimensional settings that achieves dimension reduction without imposing restrictive distributional or functional form…

Econometrics · Economics 2025-10-14 Jianhua Mei , Fu Ouyang , Thomas T. Yang

Recent years, local differential privacy (LDP) has been adopted by many web service providers like Google \cite{erlingsson2014rappor}, Apple \cite{apple2017privacy} and Microsoft \cite{bolin2017telemetry} to collect and analyse users' data…

Information Theory · Computer Science 2022-03-15 Zhongzheng Xiong , Jialin Sun , Xiaojun Mao , Jian Wang , Shan Ying , Zengfeng Huang

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in…

Multiagent Systems · Computer Science 2020-04-22 Roula Nassif , Stefan Vlaski , Ali H. Sayed

We study the Densest Subgraph (DSG) problem under the additional constraint of differential privacy. DSG is a fundamental theoretical question which plays a central role in graph analytics, and so privacy is a natural requirement. All known…

Data Structures and Algorithms · Computer Science 2024-04-09 Michael Dinitz , Satyen Kale , Silvio Lattanzi , Sergei Vassilvitskii

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…

Machine Learning · Statistics 2022-12-02 Kristian Georgiev , Samuel B. Hopkins

We give the first polynomial time and sample $(\epsilon, \delta)$-differentially private (DP) algorithm to estimate the mean, covariance and higher moments in the presence of a constant fraction of adversarial outliers. Our algorithm…

Machine Learning · Statistics 2021-12-08 Pravesh K. Kothari , Pasin Manurangsi , Ameya Velingker

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…

Machine Learning · Computer Science 2019-04-17 Di Wang , Jinhui Xu

One of the founding paradigms of machine learning is that a small number of variables is often sufficient to describe high-dimensional data. The minimum number of variables required is called the intrinsic dimension (ID) of the data.…

Machine Learning · Statistics 2020-07-14 Michele Allegra , Elena Facco , Francesco Denti , Alessandro Laio , Antonietta Mira

Differential privacy is becoming a gold standard for privacy research; it offers a guaranteed bound on loss of privacy due to release of query results, even under worst-case assumptions. The theory of differential privacy is an active…

Private closeness testing asks to decide whether the underlying probability distributions of two sensitive datasets are identical or differ significantly in statistical distance, while guaranteeing (differential) privacy of the data. As in…

Data Structures and Algorithms · Computer Science 2023-09-14 Clément L. Canonne , Yucheng Sun

The bootstrap is a popular data-driven method to quantify statistical uncertainty, but for modern high-dimensional problems, it could suffer from huge computational costs due to the need to repeatedly generate resamples and refit models. We…

Methodology · Statistics 2023-06-21 Henry Lam , Zhenyuan Liu
‹ Prev 1 4 5 6 7 8 10 Next ›