Concentration Inequalities for Statistical Inference
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Weighted Lasso estimates for sparse logistic regression: non-asymptotic properties with measurement errorsActa Mathematica Scientia, 2020
- Sub‐Weibull distributions: Generalizing sub‐Gaussian and sub‐Exponential properties to heavier tailed distributionsStat, 2020
- On norms in some class of exponential type Orlicz spaces of random variablesPositivity, 2019
- The Bennett-Orlicz NormSankhya A, 2017
- High dimensional robust M-estimation: asymptotic variance via approximate message passingProbability Theory and Related Fields, 2015
- Large Sample Covariance Matrices and High-Dimensional Data Analysis2015
- Notes on discrete compound Poisson model with applications to risk theoryInsurance: Mathematics and Economics, 2014
- On robust regression with high-dimensional predictorsProceedings of the National Academy of Sciences, 2013
- Tail Bounds for the Suprema of Empirical Processes over Unbounded Classes of FunctionsActa Mathematica Sinica, English Series, 2005
- Sums and Gaussian Vectors1995