随机向量均值估计的无维数 PAC-Bayesian 界
统计理论
2018-02-14 v1 统计理论
摘要
在本文中，我们提出了一种通过对范数应用某种阈值函数来计算的随机向量均值的新估计量。在弱矩假设下，利用 PAC-Bayesian 不等式，证明了非渐近的无维数近似次高斯界。
引用
@article{arxiv.1802.04308,
title = {Dimension-free PAC-Bayesian bounds for the estimation of the mean of a random vector},
author = {Olivier Catoni and Ilaria Giulini},
journal= {arXiv preprint arXiv:1802.04308},
year = {2018}
}
备注
31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. Selected for oral presentation in the NIPS 2017 workshop "(Almost) 50 Shades of Bayesian Learning: PAC-Bayesian trends and insights", December 9, 2017. Workshop URL : https://bguedj.github.io/nips2017/50shadesbayesian.html