Concentration inequalities for statistical inference
From MaRDI portal
Publication:3380883
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.
Recommendations
Cites work
- scientific article; zbMATH DE number 4170917 (Why is no real title available?)
- scientific article; zbMATH DE number 3818776 (Why is no real title available?)
- scientific article; zbMATH DE number 3945130 (Why is no real title available?)
- scientific article; zbMATH DE number 44577 (Why is no real title available?)
- scientific article; zbMATH DE number 49190 (Why is no real title available?)
- scientific article; zbMATH DE number 3504209 (Why is no real title available?)
- scientific article; zbMATH DE number 1302647 (Why is no real title available?)
- scientific article; zbMATH DE number 952381 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1419973 (Why is no real title available?)
- scientific article; zbMATH DE number 6026126 (Why is no real title available?)
- A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
- A tail inequality for quadratic forms of subgaussian random vectors
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- A two-sample test for high-dimensional data with applications to gene-set testing
- An Introduction to Heavy-Tailed and Subexponential Distributions
- Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator
- Asymptotic Statistics
- Asymptotic theory for differentially private generalized \(\beta\)-models with parameters increasing
- Asymptotics for high dimensional regression \(M\)-estimates: fixed design results
- Concentration and moment inequalities for polynomials of independent random variables
- Concentration inequalities for order statistics
- Concentration inequalities. A nonasymptotic theory of independence
- DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
- Elastic-net Regularized High-dimensional Negative Binomial Regression: Consistency and Weak Signal Detection
- Exponential integrability of sub-Gaussian vectors
- Hanson-Wright inequality and sub-Gaussian concentration
- High dimensional robust M-estimation: asymptotic variance via approximate message passing
- High-dimensional probability. An introduction with applications in data science
- High-dimensional statistics. A non-asymptotic viewpoint
- Honest variable selection in linear and logistic regression models via \(\ell _{1}\) and \(\ell _{1}+\ell _{2}\) penalization
- Kullback-Leibler aggregation and misspecified generalized linear models
- L1 least squares for sparse high-dimensional LDA
- Large sample covariance matrices and high-dimensional data analysis
- Lasso guarantees for \(\beta \)-mixing heavy-tailed time series
- Learning Bounds for Kernel Regression Using Effective Data Dimensionality
- Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
- Linear hypothesis testing in dense high-dimensional linear models
- Log-concave probability and its applications
- Log-concavity and strong log-concavity: a review
- Mathematical foundations of infinite-dimensional statistical models
- Non-asymptotic oracle inequalities for the high-dimensional Cox regression via Lasso
- Nonparametric statistics for stochastic processes. Estimation and prediction.
- Notes on discrete compound Poisson model with applications to risk theory
- On learning with integral operators
- On robust regression with high-dimensional predictors
- On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
- Oracle inequalities for the lasso in the Cox model
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Probability
- Probability Inequalities for Sums of Bounded Random Variables
- Probability Inequalities for the Sum of Independent Random Variables
- Random matrices: sharp concentration of eigenvalues
- Rate minimaxity of the Lasso and Dantzig selector for the \(l_{q}\) loss in \(l_{r}\) balls
- Sharper bounds for Gaussian and empirical processes
- Simultaneous analysis of Lasso and Dantzig selector
- Sparse estimation in Ising model via penalized Monte Carlo methods
- Square-root Lasso for high-dimensional sparse linear systems with weakly dependent errors
- Statistical foundations of data science
- Statistics for high-dimensional data. Methods, theory and applications.
- Sums and Gaussian vectors
- Tail bounds for the supremums of empirical processes over unbounded classes of functions
- Tests for high-dimensional regression coefficients with factorial designs
- The Bennett-Orlicz norm
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
- The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality
- Univariate Discrete Distributions
- Upper (lower) bounds on the mean of the maximum (minimum) of a number of random variables
- Weak convergence and empirical processes. With applications to statistics
- Weighted Lasso estimates for sparse logistic regression: non-asymptotic properties with measurement errors
- \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
Cited in
(19)- Concentration inequalities for upper probabilities
- On the sub-Gaussianity of the missing mass
- Elastic-net Regularized High-dimensional Negative Binomial Regression: Consistency and Weak Signal Detection
- Concentration inequality of maximum likelihood estimator
- Asymptotic normality and confidence region for Catoni's Z estimator
- Concentration inequalities for non-causal random fields
- Optimal distribution-free concentration for the log-likelihood function of Bernoulli variables
- scientific article; zbMATH DE number 4169843 (Why is no real title available?)
- Asymptotics in the Thurstone model with an increasing items
- Concentration inequalities, counting processes and adaptive statistics
- Asymptotic in the ordered networks with a noisy degree sequence
- Oracle inequalities for weighted group Lasso in high-dimensional Poisson regression model
- scientific article; zbMATH DE number 168795 (Why is no real title available?)
- Asymptotics in the Thurstone model with an increasing items
- Some applications of concentration inequalities to statistics
- Concentration inequalities of MLE and robust MLE
- Concentration inequalities and laws of large numbers under epistemic and regular irrelevance
- Non-asymptotic sub-Gaussian error bounds for hypothesis testing
- Asymptotic theory in network models with covariates and a growing number of node parameters
This page was built for publication: Concentration inequalities for statistical inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3380883)
