Search Results for author:
Found 8 papers, 1 papers with code
Efficient median of means estimator
The goal of this note is to present a modification of the popular median of means estimator that achieves sub-Gaussian deviation bounds with nearly optimal constants under minimal assumptions on the underlying distribution.
Minimax Supervised Clustering in the Anisotropic Gaussian Mixture Model: A new take on Robust Interpolation
Our analysis also shows that interpolation can be robust to corruption in the covariance of the noise when the signal is aligned with the "clean" part of the covariance, for the properly defined notion of alignment.
Asymptotic normality of robust risk minimizers
This paper investigates asymptotic properties of algorithms that can be viewed as robust analogues of the classical empirical risk minimization.
Excess risk bounds in robust empirical risk minimization
We propose a version of empirical risk minimization based on the idea of replacing sample averages by robust proxies of the expectation, and obtain high-confidence bounds for the excess risk of resulting estimators.
User-Friendly Covariance Estimation for Heavy-Tailed Distributions
We offer a survey of recent results on covariance estimation for heavy-tailed distributions.
Methodology Statistics Theory Statistics Theory
Distributed Statistical Estimation and Rates of Convergence in Normal Approximation
This paper presents a class of new algorithms for distributed statistical estimation that exploit divide-and-conquer approach.
Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries
As is now well known, the sample mean then may have a catastrophically bad performance..." Motivated by this question, we develop a new estimator of the (element-wise) mean of a random matrix, which includes covariance estimation problem as a special case.
Robust and Scalable Bayes via a Median of Subset Posterior Measures
We propose a novel approach to Bayesian analysis that is provably robust to outliers in the data and often has computational advantages over standard methods.
