Robust multivariate mean estimation: The optimality of trimmed mean

We consider the problem of estimating the mean of a random vector based on i.i.d. observations and adversarial contamination. We introduce a multivariate extension of the trimmed-mean estimator and show its optimal performance under minimal conditions.

[1]  P. Bickel.  On Some Robust Estimates of Location , 1965 .

[2]  S. Stigler.  The Asymptotic Distribution of the Trimmed Mean , 1973 .

[3]  J. Hoffmann-jorgensen.  Probability in Banach Space , 1977 .

[4]  E. Giné,et al.  Some Limit Theorems for Empirical Processes , 1984 .

[5]  Leslie G. Valiant,et al.  Learning Disjunction of Conjunctions , 1985, IJCAI.

[6]  Ming Li,et al.  Learning in the presence of malicious errors , 1993, STOC '88.

[7]  M. Talagrand.  New concentration inequalities in product spaces , 1996 .

[8]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[9]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[10]  J. Tukey,et al.  LESS VULNERABLE CONFIDENCE AND SIGNIFICANCE PROCEDURES FOR LOCATION BASED ON A SINGLE SAMPLE : TRIMMING/WINSORIZATION 1 , 2016 .

[11]  Daniel M. Kane,et al.  Robust Estimators in High Dimensions without the Computational Intractability , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[12]  Jerry Li,et al.  Being Robust (in High Dimensions) Can Be Practical , 2017, ICML.

[13]  Matthieu Lerasle,et al.  ROBUST MACHINE LEARNING BY MEDIAN-OF-MEANS: THEORY AND PRACTICE , 2019 .

[14]  Jerry Li,et al.  Robustly Learning a Gaussian: Getting Optimal Error, Efficiently , 2017, SODA.

[15]  Samuel B. Hopkins.  Sub-Gaussian Mean Estimation in Polynomial Time , 2018, ArXiv.

[16]  Gregory Valiant,et al.  Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers , 2017, ITCS.

[17]  Stanislav Minsker.  Uniform bounds for robust mean estimators , 2018, 1812.03523.

[18]  M. Valdora,et al.  The breakdown point of the median of means tournament , 2019, Statistics & Probability Letters.

[19]  Shahar Mendelson,et al.  Mean Estimation and Regression Under Heavy-Tailed Distributions: A Survey , 2019, Found. Comput. Math..

[20]  G. Lugosi,et al.  Sub-Gaussian estimators of the mean of a random vector , 2017, The Annals of Statistics.

[21]  G. Lecu'e,et al.  Robust sub-Gaussian estimation of a mean vector in nearly linear time , 2019, The Annals of Statistics.