A general decision theory for Huber's -contamination model

DOI10.1214/16-EJS1216zbMATH Open1357.62038arXiv1511.04144OpenAlexW2962713494MaRDI QIDQ502837FDOQ502837

Authors: Mengjie Chen, Chao Gao, Zhao Ren 

Publication date: 11 January 2017

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: Today's data pose unprecedented challenges to statisticians. It may be incomplete, corrupted or exposed to some unknown source of contamination. We need new methods and theories to grapple with these challenges. Robust estimation is one of the revived fields with potential to accommodate such complexity and glean useful information from modern datasets. Following our recent work on high dimensional robust covariance matrix estimation, we establish a general decision theory for robust statistics under Huber's $epsilon$-contamination model. We propose a solution using Scheff{'e} estimate to a robust two-point testing problem that leads to the construction of robust estimators adaptive to the proportion of contamination. Applying the general theory, we construct robust estimators for nonparametric density estimation, sparse linear regression and low-rank trace regression. We show that these new estimators achieve the minimax rate with optimal dependence on the contamination proportion. This testing procedure, Scheff{'e} estimate, also enjoys an optimal rate in the exponent of the testing error, which may be of independent interest.

Full work available at URL: https://arxiv.org/abs/1511.04144

Recommendations

• Robust covariance and scatter matrix estimation under Huber's contamination model
• Robust regression via mutivariate regression depth
• Robust estimation under heavy contamination using unnormalized models
• New statistical robust estimators, open problems
• On Huber's contaminated model

zbMATH Keywords

density estimationrobust statisticsminimax ratesparse linear regressionrobust testingtrace regression

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Estimation in multivariate analysis (62H12) Minimax procedures in statistical decision theory (62C20)

Cited In (19)

• Excess-risk consistency of group-hard thresholding estimator in robust estimation of Gaussian mean
• Robust regression via mutivariate regression depth
• On robustness and local differential privacy
• High-dimensional robust precision matrix estimation: cellwise corruption under \(\epsilon \)-contamination
• Robust and tuning-free sparse linear regression via square-root slope
• Robustness and Tractability for Non-convex M-estimators
• All-in-one robust estimator of the Gaussian mean
• Confidence regions and minimax rates in outlier-robust estimation on the probability simplex
• ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
• Robust estimation under heavy contamination using unnormalized models
• On density estimation at a fixed point under local differential privacy
• Detecting strong signals in gene perturbation experiments: an adaptive approach with power guarantee and FDR control
• Multidimensional linear functional estimation in sparse Gaussian models and robust estimation of the mean
• On Huber's contaminated model
• Robust multivariate mean estimation: the optimality of trimmed mean
• Robust and efficient mean estimation: an approach based on the properties of self-normalized sums
• Density estimation with contamination: minimax rates and theory of adaptation
• A minimax framework for quantifying risk-fairness trade-off in regression
• Generalized resilience and robust statistics

This page was built for publication: A general decision theory for Huber's \(\epsilon\)-contamination model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q502837)