Error bounds of Median-of-means estimators with VC-dimension

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yuxuan, Chen, Yiming, Wang, Hanchao, Zhang, Lixin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917480080867328
author Wang, Yuxuan
Chen, Yiming
Wang, Hanchao
Zhang, Lixin
author_facet Wang, Yuxuan
Chen, Yiming
Wang, Hanchao
Zhang, Lixin
contents We obtain the upper error bounds of robust estimators for mean vector, using the median-of-means (MOM) method. The method is designed to handle data with heavy tails and contamination, with only a finite second moment, which is weaker than many others, relying on the VC dimension rather than the Rademacher complexity to measure statistical complexity. This allows us to implement MOM in covariance estimation, without imposing conditions such as $L$-sub-Gaussian or $L_{4}-L_{2}$ norm equivalence. In particular, we derive a new robust estimator, the MOM version of the halfspace depth, along with error bounds for mean estimation in any norm.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03410
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Error bounds of Median-of-means estimators with VC-dimension
Wang, Yuxuan
Chen, Yiming
Wang, Hanchao
Zhang, Lixin
Statistics Theory
We obtain the upper error bounds of robust estimators for mean vector, using the median-of-means (MOM) method. The method is designed to handle data with heavy tails and contamination, with only a finite second moment, which is weaker than many others, relying on the VC dimension rather than the Rademacher complexity to measure statistical complexity. This allows us to implement MOM in covariance estimation, without imposing conditions such as $L$-sub-Gaussian or $L_{4}-L_{2}$ norm equivalence. In particular, we derive a new robust estimator, the MOM version of the halfspace depth, along with error bounds for mean estimation in any norm.
title Error bounds of Median-of-means estimators with VC-dimension
topic Statistics Theory
url https://arxiv.org/abs/2409.03410