arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11734stat.MLcs.LGmath.STstat.TH
收藏

VC维抗差次高斯估计

Robust subgaussian estimation with VC-dimension

CREST(统计与经济建模研究中心);ENSAE(法国国立统计与经济管理学院);IPParis(巴黎综合理工学院)

Jules Depersin

摘要:

基于均值中值(Median-of-Means,简称MEN)的程序提供了非渐近和强偏差界,即使数据是重尾和/或损坏的。本文提出了一种新的一般性方法来约束估计量的超额风险。其核心技术是使用VC维(而不是拉德马赫复杂度)来衡量统计复杂度。特别是,这允许给第一个强大的估计稀疏估计,实现所谓的亚高斯率只假设一个有限的二阶矩的未损坏的数据。相比之下,以前的作品使用拉德马赫复杂度需要一个有限的时刻,增长的维数。利用这种技术,我们得到了新的鲁棒Sugaussian界的均值估计在任何范数。我们还得到了一个新的稳健估计的协方差估计,这是第一次实现亚高斯界没有$L_4-L_2$范数等价。

英文摘要:

Median-of-means (MOM) based procedures provide non-asymptotic and strong deviation bounds even when data are heavy-tailed and/or corrupted. This work proposes a new general way to bound the excess risk for MOM estimators. The core technique is the use of VC-dimension (instead of Rademacher complexity) to measure the statistical complexity. In particular, this allows to give the first robust estimators for sparse estimation which achieves the so-called subgaussian rate only assuming a finite second moment for the uncorrupted data. By comparison, previous works using Rademacher complexities required a number of finite moments that grows logarithmically with the dimension. With this technique, we derive new robust sugaussian bounds for mean estimation in any norm. We also derive a new robust estimator for covariance estimation that is the first to achieve subgaussian bounds without $L_4-L_2$ norm equivalence.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑