English
Related papers

Related papers: When does the Tukey median work?

200 papers

Robust estimation under Huber's $\epsilon$-contamination model has become an important topic in statistics and theoretical computer science. Statistically optimal procedures such as Tukey's median and other estimators based on depth…

Machine Learning · Statistics 2019-02-27 Chao Gao , Jiyi Liu , Yuan Yao , Weizhi Zhu

The Tukey (or halfspace) depth extends nonparametric methods toward multivariate data. The multivariate analogues of the quantiles are the central regions of the Tukey depth, defined as sets of points in the $d$-dimensional space whose…

Computation · Statistics 2024-09-30 Vít Fojtík , Petra Laketa , Pavlo Mozharovskyi , Stanislav Nagy

Mean estimation is a fundamental task in statistics and a focus within differentially private statistical estimation. While univariate methods based on the Gaussian mechanism are widely used in practice, more advanced techniques such as the…

Machine Learning · Computer Science 2025-02-27 Gavin Brown , Lydia Zakynthinou

As estimators of location parameters, univariate trimmed means are well known for their robustness and efficiency. They can serve as robust alternatives to the sample mean while possessing high efficiencies at normal as well as heavy-tailed…

Statistics Theory · Mathematics 2007-06-13 Yijun Zuo

Advances in computing power enable more widespread use of the mode, which is a natural measure of central tendency since, as the most probable value, it is not influenced by the tails in the distribution. The properties of the half-sample…

Statistics Theory · Mathematics 2007-06-13 David R. Bickel , Rudolf Fruehwirth

The problem of robust mean estimation in high dimensions is studied, in which a certain fraction (less than half) of the datapoints can be arbitrarily corrupted. Motivated by compressive sensing, the robust mean estimation problem is…

Applications · Statistics 2022-12-08 Aditya Deshmukh , Jing Liu , Venugopal V. Veeravalli

We study the problem of robust estimation under heterogeneous corruption rates, where each sample may be independently corrupted with a known but non-identical probability. This setting arises naturally in distributed and federated…

Machine Learning · Computer Science 2025-10-02 Syomantak Chaudhuri , Jerry Li , Thomas A. Courtade

We study Gaussian sparse estimation tasks in Huber's contamination model with a focus on mean estimation, PCA, and linear regression. For each of these tasks, we give the first sample and computationally efficient robust estimators with…

Machine Learning · Computer Science 2024-03-18 Ilias Diakonikolas , Daniel M. Kane , Sushrut Karmalkar , Ankit Pensia , Thanasis Pittas

The computation of the Tukey depth, also called halfspace depth, is very demanding, even in low dimensional spaces, because it requires the consideration of all possible one-dimensional projections. In this paper we propose a random depth…

Computation · Statistics 2007-07-03 J. A. Cuesta-Albertos , A. Nieto-Reyes

This article introduces trimmed estimators for the mean and covariance function of general functional data. The estimators are based on a new measure of outlyingness or data depth that is well defined on any metric space, although this…

Methodology · Statistics 2012-12-03 Daniel Gervini

Tukey's halfspace depth can be seen as a stochastic program and as such it is not guarded against optimizer's curse, so that a limited training sample may easily result in a poor out-of-sample performance. We propose a generalized halfspace…

Optimization and Control · Mathematics 2024-05-13 Jevgenijs Ivanovs , Pavlo Mozharovskyi

The median absolute deviation (MAD) is a popular robust measure of statistical dispersion. However, when it is applied to non-parametric distributions (especially multimodal, discrete, or heavy-tailed), lots of statistical inference issues…

Methodology · Statistics 2022-08-30 Andrey Akinshin

Tukey depth regions are important notions in nonparametric multivariate data analysis. A $\tau$-th Tukey depth region $\mathcal{D}_{\tau}$ is the set of all points that have at least depth $\tau$. While the Tukey depth regions are easily…

Computation · Statistics 2014-04-17 Xiaohui Liu

The scatter halfspace depth (sHD) is an extension of the location halfspace (also called Tukey) depth that is applicable in the nonparametric analysis of scatter. Using sHD, it is possible to define minimax optimal robust scatter estimators…

Computation · Statistics 2022-08-11 Xiaohui Liu , Yuzi Liu , Petra Laketa , Stanislav Nagy , Yuting Chen

We give the first dimensionality reduction methods for the overconstrained Tukey regression problem. The Tukey loss function $\|y\|_M = \sum_i M(y_i)$ has $M(y_i) \approx |y_i|^p$ for residual errors $y_i$ smaller than a prescribed…

Data Structures and Algorithms · Computer Science 2019-05-15 Kenneth L. Clarkson , Ruosong Wang , David P. Woodruff

We formalize notions of robustness for composite estimators via the notion of a breakdown point. A composite estimator successively applies two (or more) estimators: on data decomposed into disjoint parts, it applies the first estimator on…

Machine Learning · Computer Science 2016-09-06 Pingfan Tang , Jeff M. Phillips

The geometric median covariation matrix is a robust multivariate indicator of dispersion which can be extended without any difficulty to functional data. We define estimators, based on recursive algorithms, that can be simply updated at…

Statistics Theory · Mathematics 2016-07-12 Hervé Cardot , Antoine Godichon-Baggioni

This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Dabiao Ma , Zhiba Su , Jian Yang , Haojun Fei

We revisit the problem of estimating the mean of a high-dimensional distribution in the presence of an $\varepsilon$-fraction of adversarial outliers. When $\varepsilon$ is at most some sufficiently small constant, previous works can…

Data Structures and Algorithms · Computer Science 2024-11-22 Hongjie Chen , Deepak Narayanan Sridharan , David Steurer

Existing algorithms for subgroup discovery with numerical targets do not optimize the error or target variable dispersion of the groups they find. This often leads to unreliable or inconsistent statements about the data, rendering practical…

Artificial Intelligence · Computer Science 2017-07-06 Mario Boley , Bryan R. Goldsmith , Luca M. Ghiringhelli , Jilles Vreeken