On least squares estimation under heteroscedastic and heavy-tailed errors

DOI10.1214/21-AOS2105zbMath1486.62113arXiv1909.02088OpenAlexW2971447570MaRDI QIDQ2119229

Arun Kumar Kuchibhotla, Rohit Kumar Patra

Publication date: 23 March 2022

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1909.02088

zbMATH Keywords

heavy tailsmaximal inequalityinterpolation inequalitydyadic peelingfinite sample tail probability boundslocal envelopes

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Inequalities; stochastic orderings (60E15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Performance of empirical risk minimization in linear aggregation
• Upper bounds on product and multiplier empirical processes
• On higher order isotropy conditions and lower bounds for sparse quadratic forms
• Empirical entropy, minimax regret and minimax risk
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Linear smoothers and additive models
• On singular solutions of nonlinear elliptic and parabolic equations
• Robust linear least squares regression
• Global risk bounds and adaptation in univariate convex regression
• Risk bounds for statistical learning
• Empirical risk minimization for heavy-tailed losses
• The Grenander estimator: A nonasymptotic approach
• Estimating a regression function
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Rates of convergence for minimum contrast estimators
• The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
• Convergence rate of sieve estimates
• Consistency for the least squares estimator in nonparametric regression
• Information-theoretic determination of minimax rates of convergence
• ``Local vs. ``global parameters -- breaking the Gaussian complexity barrier
• On concentration for (regularized) empirical risk minimization
• On univariate convex regression
• Adaptive risk bounds in unimodal regression
• Nonparametric shape-restricted regression
• Sharp oracle inequalities for least squares estimators in shape restricted regression
• A distribution-free theory of nonparametric regression
• Structure adaptive approach for dimension reduction.
• Risk bounds in isotonic regression
• Weak convergence and empirical processes. With applications to statistics
• A local maximal inequality under uniform entropy
• Bracketing numbers of convex and \(m\)-monotone functions on polytopes
• On estimation of isotonic piecewise constant signals
• Robust machine learning by median-of-means: theory and practice
• Risk minimization by median-of-means tournaments
• Convergence rates of least squares regression estimators with heavy-tailed errors
• Isotonic regression in general dimensions
• Comparison and anti-concentration bounds for maxima of Gaussian random vectors
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• On weakly bounded empirical processes
• Concentration inequalities and asymptotic results for ratio type empirical processes
• On risk bounds in isotonic and other shape restricted regression problems
• Tail bounds via generic chaining
• Majorizing measures: The generic chaining
• Bracketing metric entropy rates and empirical central limit theorems for function classes of Besov- and Sobolev-type
• Learning without Concentration
• Concentration Inequalities
• Nemirovski's Inequalities Revisited
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
• Central limit theorems and weak laws of large numbers in certain banach spaces
• Asymptotic Statistics
• Sieve Extremum Estimates for Weakly Dependent Data
• An Unrestricted Learning Procedure
• Upper and Lower Bounds for Stochastic Processes
• Around Nemirovski’s inequality
• Convergence of stochastic processes

This page was built for publication: On least squares estimation under heteroscedastic and heavy-tailed errors