Recent Advances in Algorithmic High-Dimensional Robust Statistics

Understand

Learning in the presence of outliers is a fundamental problem in statistics.

• Until recently, all known efficient unsupervised learning algorithms were very sensitive to outliers in high dimensions.
• In particular, even for the task of robust mean estimation under natural distributional assumptions, no efficient algorithm was known.
• Recent work in theoretical computer science gave the first efficient robust estimators for a number of fundamental statistical tasks, including mean and covariance estimation.