通过迭代滤波进行异常值鲁棒的高维稀疏估计

Nov, 2019

Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering

Ilias Diakonikolas, Sushrut Karmalkar, Daniel Kane, Eric Price, Alistair Stewart

TL;DR研究高维稀疏估计任务中的鲁棒性问题，提出使用基于谱技术的迭代式方法消除数据中的离群值，实现高效稳健的稀疏均值估计和稀疏主成分分析。

Abstract

We study high-dimensional sparse estimation tasks in a robust setting where a constant fraction of the dataset is adversarially corrupted.