High-Dimensional Robust Mean Estimation in Nearly-Linear Time
SODA '19: Symposium on Discrete Algorithms San Diego California January, 2019, pp. 2755-2771, 2019.
We study the fundamental problem of high-dimensional mean estimation in a robust model where a constant fraction of the samples are adversarially corrupted. Recent work gave the first polynomial time algorithms for this problem with dimension-independent error guarantees for several families of structured distributions. In this work, we ...More
Full Text (Upload PDF)
PPT (Upload PPT)