Concentration Inequalities for Statistical Inference

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Huiming, Chen, Song Xi
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929722906116096
author Zhang, Huiming
Chen, Song Xi
author_facet Zhang, Huiming
Chen, Song Xi
contents This paper gives a review of concentration inequalities which are widely employed in non-asymptotical analyses of mathematical statistics in a wide range of settings, from distribution-free to distribution-dependent, from sub-Gaussian to sub-exponential, sub-Gamma, and sub-Weibull random variables, and from the mean to the maximum concentration. This review provides results in these settings with some fresh new results. Given the increasing popularity of high-dimensional data and inference, results in the context of high-dimensional linear and Poisson regressions are also provided. We aim to illustrate the concentration inequalities with known constants and to improve existing bounds with sharper constants.
format Preprint
id arxiv_https___arxiv_org_abs_2011_02258
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Concentration Inequalities for Statistical Inference
Zhang, Huiming
Chen, Song Xi
Statistics Theory
Machine Learning
Probability
60F10, 60G50, 62E17
This paper gives a review of concentration inequalities which are widely employed in non-asymptotical analyses of mathematical statistics in a wide range of settings, from distribution-free to distribution-dependent, from sub-Gaussian to sub-exponential, sub-Gamma, and sub-Weibull random variables, and from the mean to the maximum concentration. This review provides results in these settings with some fresh new results. Given the increasing popularity of high-dimensional data and inference, results in the context of high-dimensional linear and Poisson regressions are also provided. We aim to illustrate the concentration inequalities with known constants and to improve existing bounds with sharper constants.
title Concentration Inequalities for Statistical Inference
topic Statistics Theory
Machine Learning
Probability
60F10, 60G50, 62E17
url https://arxiv.org/abs/2011.02258