On concentration inequalities for vector-valued Lipschitz functions

Dimitrios Katselis; Xiaotian Xie; Carolyn L. Beck; R. Srikant

doi:10.1016/j.spl.2021.109071

On concentration inequalities for vector-valued Lipschitz functions

Dimitrios Katselis, Xiaotian Xie, Carolyn L. Beck, R. Srikant

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

Abstract

We derive two upper bounds for the probability of deviation of a vector-valued Lipschitz function of a collection of random variables from its expected value. The resulting upper bounds can be tighter than bounds obtained by a direct application of a classical theorem due to Bobkov and Götze.

Original language	English (US)
Article number	109071
Journal	Statistics and Probability Letters
Volume	173
DOIs	https://doi.org/10.1016/j.spl.2021.109071
State	Published - Jun 2021

Keywords

Concentration
Markov chain
Theorem of Bobkov and Götze
Transportation cost inequality

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Online availability

10.1016/j.spl.2021.109071

Library availability

Discover UIUC Full Text

Cite this

@article{ecda1b52120148efab00a126bf6f78c5,

title = "On concentration inequalities for vector-valued Lipschitz functions",

abstract = "We derive two upper bounds for the probability of deviation of a vector-valued Lipschitz function of a collection of random variables from its expected value. The resulting upper bounds can be tighter than bounds obtained by a direct application of a classical theorem due to Bobkov and G{\"o}tze.",

keywords = "Concentration, Markov chain, Theorem of Bobkov and G{\"o}tze, Transportation cost inequality",

author = "Dimitrios Katselis and Xiaotian Xie and Beck, \{Carolyn L.\} and R. Srikant",

note = "This work was supported by the ONR, USA N00014-19-1-2566 .",

year = "2021",

month = jun,

doi = "10.1016/j.spl.2021.109071",

language = "English (US)",

volume = "173",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - On concentration inequalities for vector-valued Lipschitz functions

AU - Katselis, Dimitrios

AU - Xie, Xiaotian

AU - Beck, Carolyn L.

AU - Srikant, R.

N1 - This work was supported by the ONR, USA N00014-19-1-2566 .

PY - 2021/6

Y1 - 2021/6

N2 - We derive two upper bounds for the probability of deviation of a vector-valued Lipschitz function of a collection of random variables from its expected value. The resulting upper bounds can be tighter than bounds obtained by a direct application of a classical theorem due to Bobkov and Götze.

AB - We derive two upper bounds for the probability of deviation of a vector-valued Lipschitz function of a collection of random variables from its expected value. The resulting upper bounds can be tighter than bounds obtained by a direct application of a classical theorem due to Bobkov and Götze.

KW - Concentration

KW - Markov chain

KW - Theorem of Bobkov and Götze

KW - Transportation cost inequality

UR - https://www.scopus.com/pages/publications/85102888676

UR - https://www.scopus.com/inward/citedby.url?scp=85102888676&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2021.109071

DO - 10.1016/j.spl.2021.109071

M3 - Article

AN - SCOPUS:85102888676

SN - 0167-7152

VL - 173

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

M1 - 109071

ER -

On concentration inequalities for vector-valued Lipschitz functions

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this