English
Related papers

Related papers: High-Dimensional Robust Mean Estimation with Untru…

200 papers

We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\zeta\geq0$…

Machine Learning · Computer Science 2024-02-20 Chenlu Ye , Rui Yang , Quanquan Gu , Tong Zhang

Robustness is a key requirement for widespread deployment of machine learning algorithms, and has received much attention in both statistics and computer science. We study a natural model of robustness for high-dimensional statistical…

Machine Learning · Computer Science 2020-06-03 Pranjal Awasthi , Xue Chen , Aravindan Vijayaraghavan

Asymmetry along with heteroscedasticity or contamination often occurs with the growth of data dimensionality. In ultra-high dimensional data analysis, such irregular settings are usually overlooked for both theoretical and computational…

Statistics Theory · Mathematics 2022-07-20 Bin Luo , Xiaoli Gao

In this paper, we address the problem of conducting statistical inference in settings involving large-scale data that may be high-dimensional and contaminated by outliers. The high volume and dimensionality of the data require distributed…

Machine Learning · Statistics 2022-11-30 Emadaldin Mozafari-Majd , Visa Koivunen

A fundamental challenge in semi-supervised learning lies in the observed data's disproportional size when compared with the size of the data collected with missing outcomes. An implicit understanding is that the dataset with missing…

Methodology · Statistics 2026-05-12 Yuqian Zhang , Jelena Bradic

This paper studies the problem of multivariate linear regression where a portion of the observations is grossly corrupted or is missing, and the magnitudes and locations of such occurrences are unknown in priori. To deal with this problem,…

Machine Learning · Statistics 2017-01-12 Xiaowei Zhang , Chi Xu , Yu Zhang , Tingshao Zhu , Li Cheng

It is well-known that trimmed sample means are robust against heavy tails and data contamination. This paper analyzes the performance of trimmed means and related methods in two novel contexts. The first one consists of estimating…

Statistics Theory · Mathematics 2025-12-03 Roberto I. Oliveira , Lucas Resende

We endeavour to estimate numerous multi-dimensional means of various probability distributions on a common space based on independent samples. Our approach involves forming estimators through convex combinations of empirical means derived…

Machine Learning · Statistics 2025-03-11 Gilles Blanchard , Jean-Baptiste Fermanian , Hannah Marienwald

In this work, we study the problem of community detection in the stochastic block model with adversarial node corruptions. Our main result is an efficient algorithm that can tolerate an $\epsilon$-fraction of corruptions and achieves error…

Data Structures and Algorithms · Computer Science 2022-07-26 Allen Liu , Ankur Moitra

We consider the problem of estimating the mean of a random vector based on $N$ independent, identically distributed observations. We prove the existence of an estimator that has a near-optimal error in all directions in which the variance…

Statistics Theory · Mathematics 2020-10-23 Gabor Lugosi , Shahar Mendelson

Distributionally robust optimization (DRO) has become a powerful framework for estimation under uncertainty, offering strong out-of-sample performance and principled regularization. In this paper, we propose a DRO-based method for linear…

Machine Learning · Statistics 2025-05-06 Liviu Aolaritei , Soroosh Shafiee , Florian Dörfler

Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions…

Machine Learning · Computer Science 2017-09-26 Ananda Theertha Suresh , Felix X. Yu , Sanjiv Kumar , H. Brendan McMahan

We study the basic task of mean estimation in the presence of mean-shift contamination. In the mean-shift contamination model, an adversary is allowed to replace a small constant fraction of the clean samples by samples drawn from…

Machine Learning · Computer Science 2026-02-27 Ilias Diakonikolas , Giannis Iakovidis , Daniel M. Kane , Sihan Liu

In this work we revisit two classic high-dimensional online learning problems, namely linear regression and contextual bandits, from the perspective of adversarial robustness. Existing works in algorithmic robust statistics make strong…

Machine Learning · Computer Science 2021-06-14 Sitan Chen , Frederic Koehler , Ankur Moitra , Morris Yau

We analyze the statistical consistency of robust estimators for precision matrices in high dimensions. We focus on a contamination mechanism acting cellwise on the data matrix. The estimators we analyze are formed by plugging appropriately…

Statistics Theory · Mathematics 2015-09-25 Po-Ling Loh , Xin Lu Tan

Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence…

Machine Learning · Statistics 2014-06-20 Brian McWilliams , Gabriel Krummenacher , Mario Lucic , Joachim M. Buhmann

In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions were known, one could design an optimal sampling strategy by…

Machine Learning · Computer Science 2015-07-17 Alexandra Carpentier , Alessandro Lazaric , Mohammad Ghavamzadeh , Rémi Munos , Peter Auer , András Antos

A common approach to statistical learning with big-data is to randomly split it among $m$ machines and learn the parameter of interest by averaging the $m$ individual estimates. In this paper, focusing on empirical risk minimization, or…

Machine Learning · Statistics 2016-06-14 Jonathan Rosenblatt , Boaz Nadler

We consider an $n$ agents distributed optimization problem with imperfect information characterized in a parametric sense, where the unknown parameter can be solved by a distinct distributed parameter learning problem. Though each agent…

Optimization and Control · Mathematics 2024-04-23 Yaqun Yang , Jinlong Lei

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

Data Structures and Algorithms · Computer Science 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang