We consider stochastic optimization problems with heavy-tailed noise with structured
density. For such problems, we show that it is possible to get faster rates of convergence …

We study the fundamental task of outlier-robust mean estimation for heavy-tailed
distributions in the presence of sparsity. Specifically, given a small number of corrupted …

Recent studies have provided both empirical and theoretical evidence illustrating that heavy
tails can emerge in stochastic gradient descent (SGD) in various scenarios. Such heavy tails …

In this paper, we consider non-smooth stochastic convex optimization with two function
evaluations per round under infinite noise variance. In the classical setting when noise has …

We study principal component analysis (PCA), where given a dataset in $\mathbb R^ d $
from a distribution, the task is to find a unit vector $ v $ that approximately maximizes the …

We study the fundamental problems of Gaussian mean estimation and linear regression with
Gaussian covariates in the presence of Huber contamination. Our main contribution is the …

Conformal prediction is a generic methodology for finite-sample valid distribution-free
prediction. This technique has garnered a lot of attention in the literature partly because it …

This paper addresses the statistical problem of estimating the infinite-norm deviation from
the empirical mean to the distribution mean for high-dimensional distributions on $\{0, 1\}^ d …

Open problem: log n factor in “Local Glivenko-Cantelli” Page 1 Proceedings of Machine
Learning Research vol 195:1–3, 2023 36th Annual Conference on Learning Theory Open …

We study a mean change point testing problem for high-dimensional data, with
exponentially-or polynomially-decaying tails. In each case, depending on the $\ell_0 $-norm …