Robust multivariate mean estimation: the optimality of trimmed mean

2019/07/26 by Lugosi, Gabor, Mendelson, Shahar · 6 citations
#FOS: Mathematics #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.1907.11391

Abstract

We consider the problem of estimating the mean of a random vector based on i.i.d. observations and adversarial contamination. We introduce a multivariate extension of the trimmed-mean estimator and show its optimal performance under minimal conditions.

Cited by

• Location and scatter halfspace median under α-symmetric distributions
• Watermark Robustness and Radioactivity May Be at Odds in Federated Learning
• On the Optimality of the Median-of-Means Estimator under Adversarial Contamination
• Batched Bandits with Heavy-Tailed Rewards
• Linear Regression under Missing or Corrupted Coordinates
• Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates

Related

• Trimmed sample means for robust uniform mean estimation and regression
• Uniform bounds for robust mean estimators
• Near-optimal mean estimators with respect to general norms
• Robust high-dimensional Gaussian and bootstrap approximations for trimmed sample means
• Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination