A generalized Catoni’s M-estimator under finite α-th moment assumption with α∈(1,2)
Authors:
Open Access
- 1 January 2021
- journal article
- research article
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 15 (2) , 5523-5544
Abstract
We generalize Catoni’s M-estimator, put forward in [3] by Catoni under finite variance assumption, to the case in which distributions can have finite α-th moment with α∈(1,2). Our approach, inspired by the Taylor-like expansion developed in [4], is via slightly modifying the influence function φ in [3]. A deviation bound is established for this generalized estimator, and coincides with that in [3] as α↑2. Experiment shows that our M-estimator performs better than the empirical mean, the smaller the α is, the better the performance will be. As an application, we study an ℓ1 regression considered by Zhang et al. [19], who assumed that samples have finite variance, under finite α-th moment assumption with α∈(1,2).Keywords
This publication has 13 references indexed in Scilit:
- Mean Estimation and Regression Under Heavy-Tailed Distributions: A SurveyFoundations of Computational Mathematics, 2019
- Adaptive Huber RegressionJournal of the American Statistical Association, 2019
- Approximation of stable law in Wasserstein-1 distance by Stein’s methodThe Annals of Applied Probability, 2019
- High-Dimensional Probability2018
- Large covariance estimation through elliptical factor modelsThe Annals of Statistics, 2018
- Statistics for Process Control Engineers2017
- Bandits With Heavy TailIEEE Transactions on Information Theory, 2013
- Challenging the empirical mean and empirical variance: A deviation studyAnnales de l'Institut Henri Poincaré, Probabilités et Statistiques, 2012
- Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems2011
- Minimum Contrast Estimators on Sieves: Exponential Bounds and Rates of ConvergenceBernoulli, 1998