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 …

We present a novel approach to federated learning that endows its aggregation process with
greater robustness to potential poisoning of local data or model parameters of participating …

As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …

Big data can easily be contaminated by outliers or contain variables with heavy-tailed
distributions, which makes many conventional methods inadequate. To address this …

We provide a new computationally efficient class of estimators for risk minimization. We
show that these estimators are robust for general statistical models, under varied robustness …

We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …

Robust multivariate mean estimation: The optimality of trimmed mean Page 1 The Annals of
Statistics 2021, Vol. 49, No. 1, 393–410 https://doi.org/10.1214/20-AOS1961 © Institute of …

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 …

We consider the problem of testing for a difference in means between clusters of
observations identified via k-means clustering. In this setting, classical hypothesis tests lead …

We construct an algorithm for estimating the mean of a heavy-tailed random variable when
given an adversarial corrupted sample of N independent observations. The only assumption …