arXiv (Cornell University) · 2020 · 11 citations · 23 references
Natural SciencesData ScienceStatisticsStochastic ModelingUncertainty QuantificationEstimation TheoryOutlier DetectionRobust OptimizationRobust Statistical ModelingRobust StatisticsStatistical InferenceContamination ModelsCovarianceFailure ProbabilityFilteringGradient DescentHigh-dimensional EstimationRobust EstimationStochastic Gradient Descent
We study the problem of outlier robust high-dimensional mean estimation under a finite covariance assumption, and more broadly under finite low-degree moment assumptions. We consider a standard stability condition from the recent robust statistics literature and prove that, except with exponentially small failure probability, there exists a large fraction of the inliers satisfying this condition. As a corollary, it follows that a number of recently developed algorithms for robust mean estimation, including iterative filtering and non-convex gradient descent, give optimal error estimators with (near-)subgaussian rates. Previous analyses of these algorithms gave significantly suboptimal rates. As a corollary of our approach, we obtain the first computationally efficient algorithm with subgaussian rate for outlier-robust mean estimation in the strong contamination model under a finite covariance assumption.
23
Robust Estimation of a Location Parameter
Peter J. Huber · The Annals of Mathematical Statistics · 1964 · 7K citations · Full text
Maurice Sion · Pacific Journal of Mathematics · 1958 · 1.9K citations · Full text