Mean estimation and regression under heavy-tailed distributions: A survey

DOI10.1007/S10208-019-09427-XzbMath1431.62123arXiv1906.04280OpenAlexW2965685971WikidataQ127407171 ScholiaQ127407171MaRDI QIDQ2329044

Gábor Lugosi, Shahar Mendelson

Publication date: 17 October 2019

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.04280

zbMATH Keywords

robustnessheavy-tailed distributionsregression function estimationstatistical learningmean estimation

Mathematics Subject Classification ID

Nonparametric robustness (62G35) Nonparametric estimation (62G05) Nonparametric tolerance and confidence regions (62G15) Statistics of extreme values; tail inference (62G32)

Related Items (33)

An overview of heavy-tail extensions of multivariate Gaussian distribution and their relations ⋮ On the measure of anchored Gaussian simplices, with applications to multivariate medians ⋮ Concentration study of M-estimators using the influence function ⋮ Robust multivariate mean estimation: the optimality of trimmed mean ⋮ Posterior concentration and fast convergence rates for generalized Bayesian learning ⋮ Recovery of Sobolev functions restricted to iid sampling ⋮ Non-asymptotic analysis and inference for an outlyingness induced winsorized mean ⋮ Nonasymptotic one- and two-sample tests in high dimension with unknown covariance structure ⋮ Topics in robust statistical learning ⋮ Robustifying Markowitz ⋮ Robust tests for scatter separability beyond Gaussianity ⋮ Catoni-style confidence sequences for heavy-tailed mean estimation ⋮ Robust supervised learning with coordinate gradient descent ⋮ Dimension-free bounds for sums of independent matrices and simple tensors via the variational principle ⋮ Mean estimation in high dimension ⋮ Robust subgaussian estimation with VC-dimension ⋮ Unnamed Item ⋮ A survey of learning criteria going beyond the usual risk ⋮ Nearly optimal robust mean estimation via empirical characteristic function ⋮ The geometric median and applications to robust mean estimation ⋮ Gaussian differentially private robust mean estimation and inference ⋮ Iteratively reweighted \(\ell_1\)-penalized robust regression ⋮ Exponential concentration for geometric-median-of-means in non-positive curvature spaces ⋮ Robust statistical boosting with quantile-based adaptive loss functions ⋮ K-bMOM: A robust Lloyd-type clustering algorithm based on bootstrap median-of-means ⋮ Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence ⋮ A generalized Catoni's M-estimator under finite \(\alpha\)-th moment assumption with \(\alpha \in (1,2)\) ⋮ Robust and efficient mean estimation: an approach based on the properties of self-normalized sums ⋮ On Monte-Carlo methods in convex stochastic optimization ⋮ Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices ⋮ Consistency of invariance-based randomization tests ⋮ Learning in Repeated Auctions ⋮ Distribution-free robust linear regression

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• Performance of empirical risk minimization in linear aggregation
• A robust, adaptive M-estimator for pointwise estimation in heteroscedastic regression
• On the absolute constants in the Berry-Esseen-type inequalities
• A new method for estimation and model selection: \(\rho\)-estimation
• Sub-Gaussian mean estimators
• On the estimation of the mean of a random vector
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Robust linear least squares regression
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Empirical risk minimization for heavy-tailed losses
• Random generation of combinatorial structures from a uniform distribution
• Characterization of the law of the iterated logarithm in Banach spaces
• The space complexity of approximating the frequency moments
• Learning without concentration for general loss functions
• Sub-Gaussian estimators of the mean of a random vector
• High-dimensional robust precision matrix estimation: cellwise corruption under \(\epsilon \)-contamination
• A distribution-free theory of nonparametric regression
• Weak convergence and empirical processes. With applications to statistics
• Challenging the empirical mean and empirical variance: a deviation study
• Rho-estimators revisited: general theory and applications
• Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
• Learning from MOM's principles: Le Cam's approach
• Robust machine learning by median-of-means: theory and practice
• Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence
• Robust classification via MOM minimization
• Near-optimal mean estimators with respect to general norms
• Regularization, sparse recovery, and median-of-means tournaments
• The asymptotic distribution of the trimmed mean
• Local Rademacher complexities
• Robust multivariate mean estimation: the optimality of trimmed mean
• Learning without Concentration
• Concentration Inequalities
• Multiscale Dictionary Learning: Non-Asymptotic Bounds and Robustness
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
• Robust Estimators in High-Dimensions Without the Computational Intractability
• Neural Network Learning
• Learning from untrusted data
• An Unrestricted Learning Procedure
• Mixture models, robustness, and sum of squares proofs
• Robust moment estimation and improved clustering via sum of squares
• Efficient Algorithms and Lower Bounds for Robust Linear Regression
• An optimal (ϵ,δ)‐randomized approximation scheme for the mean of random variables with bounded relative variance
• Probability Inequalities for Sums of Bounded Random Variables
• Bandits With Heavy Tail
• Geometric median in nearly linear time
• Estimation of High Dimensional Mean Regression in the Absence of Symmetry and Light Tail Assumptions
• Robust Estimation of a Location Parameter
• On Some Robust Estimates of Location
• Introduction to nonparametric estimation
• Robust Statistics

This page was built for publication: Mean estimation and regression under heavy-tailed distributions: A survey