Sub-Gaussian estimators of the mean of a random vector

Gábor Lugosi; Shahar Mendelson

doi:10.1214/17-AOS1639

Sub-Gaussian estimators of the mean of a random vector

Gábor Lugosi, Shahar Mendelson

Research output: Contribution to journal › Article › peer-review

94 Citations (Scopus)

Abstract

We study the problem of estimating the mean of a random vector X given a sample of N independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of X exists. The estimator is based on a novel concept of a multivariate median.

Original language	English
Pages (from-to)	783-794
Number of pages	12
Journal	Annals of Statistics
Volume	47
Issue number	2
DOIs	https://doi.org/10.1214/17-AOS1639
Publication status	Published - Apr 2019

Access to Document

10.1214/17-AOS1639

Cite this

@article{0263290eed9d4bb5823fa3acda9fe038,

title = "Sub-Gaussian estimators of the mean of a random vector",

abstract = "We study the problem of estimating the mean of a random vector X given a sample of N independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of X exists. The estimator is based on a novel concept of a multivariate median.",

keywords = "Mean estimation, Robust estimation, Sub-Gaussian inequalities",

author = "G{\'a}bor Lugosi and Shahar Mendelson",

note = "Publisher Copyright: {\textcopyright} Institute of Mathematical Statistics, 2019.",

year = "2019",

month = apr,

doi = "10.1214/17-AOS1639",

language = "English",

volume = "47",

pages = "783--794",

journal = "Annals of Statistics",

issn = "0090-5364",

publisher = "Institute of Mathematical Statistics",

number = "2",

}

TY - JOUR

T1 - Sub-Gaussian estimators of the mean of a random vector

AU - Lugosi, Gábor

AU - Mendelson, Shahar

N1 - Publisher Copyright: © Institute of Mathematical Statistics, 2019.

PY - 2019/4

Y1 - 2019/4

N2 - We study the problem of estimating the mean of a random vector X given a sample of N independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of X exists. The estimator is based on a novel concept of a multivariate median.

AB - We study the problem of estimating the mean of a random vector X given a sample of N independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of X exists. The estimator is based on a novel concept of a multivariate median.

KW - Mean estimation

KW - Robust estimation

KW - Sub-Gaussian inequalities

UR - http://www.scopus.com/inward/record.url?scp=85060247701&partnerID=8YFLogxK

U2 - 10.1214/17-AOS1639

DO - 10.1214/17-AOS1639

M3 - Article

SN - 0090-5364

VL - 47

SP - 783

EP - 794

JO - Annals of Statistics

JF - Annals of Statistics

IS - 2

ER -

Sub-Gaussian estimators of the mean of a random vector

Abstract

Access to Document

Other files and links

Fingerprint

Cite this