A generalized Catoni's M-estimator under finite -th moment assumption with (1,2)

DOI10.1214/21-EJS1911zbMATH Open1493.62159arXiv2010.05008OpenAlexW4206709659WikidataQ114599189 ScholiaQ114599189MaRDI QIDQ2074299FDOQ2074299

Authors: Peng Chen, Xinghu Jin, Xiang Li, Lihu Xu 

Publication date: 9 February 2022

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: We generalize the { $mM$-estimator} put forward by Catoni in his seminal paper [C12] to the case in which samples can have finite $alpha$-th moment with $alphain(1,2)$ rather than finite variance, our approach is by slightly modifying the influence function $varphi$ therein. The choice of the new influence function is inspired by the Taylor-like expansion developed in [C-N-X]. We obtain a deviation bound of the estimator, as $alphaightarrow2$, this bound is the same as that in [C12]. Experiment shows that our generalized $mM$-estimator performs better than the empirical mean estimator, the smaller the $alpha$ is, the better the performance will be. As an application, we study an $el{l}_1$ regression considered by Zhang et al. [Z-Z] who assumed that samples have finite variance, and relax their assumption to be finite {$alpha$-th} moment with $alphain(1,2)$.

Full work available at URL: https://arxiv.org/abs/2010.05008

Recommendations

• Challenging the empirical mean and empirical variance: a deviation study
• scientific article; zbMATH DE number 1054299
• Concentration study of M-estimators using the influence function
• M-estimation for autoregression with infinite variance
• Finite sample breakdown of M- and P-estimators

zbMATH Keywords

deviation boundempirical mean\(\alpha\)-th moment\(\ell_1\) regressionCatoni's M-estimator

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric robustness (62G35)

Cites Work

• High-dimensional probability. An introduction with applications in data science
• Challenging the empirical mean and empirical variance: a deviation study
• Bandits With Heavy Tail
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$
• Large covariance estimation through elliptical factor models
• Approximation of stable law in Wasserstein-1 distance by Stein's method
• Adaptive Huber Regression
• An optimal (ϵ,δ)‐randomized approximation scheme for the mean of random variables with bounded relative variance
• Stein's method for asymmetric \(\alpha \)-stable distributions, with application to the stable CLT
• A kernel bound for non-symmetric stable distribution and its applications
• Mean estimation and regression under heavy-tailed distributions: A survey
• Robust Estimation of the Mean with Bounded Relative Standard Deviation

Cited In (3)

• Catoni-style confidence sequences for heavy-tailed mean estimation
• Robust supervised learning with coordinate gradient descent
• Asymptotic normality and confidence region for Catoni's Z estimator

This page was built for publication: A generalized Catoni's M-estimator under finite \(\alpha\)-th moment assumption with \(\alpha \in (1,2)\)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2074299)