Apr 24, 2016 · We present polynomial-time algorithms to estimate the mean and covariance with error guarantees in terms of information-theoretic lower bounds.

Mean: The median xmed. = mediani{xi} satisfies. |xmedian| = O(η + )σ with probability 1 − 1/ poly(n). Variance: There is an algorithm that computes in polyno-.

Aug 14, 2016 · The mean and covariance of a probability distribution are its most basic parameters (if they are bounded). Many families of distributions are ...

We consider the problem of estimating the mean and covariance of a distribution from i.i.d. samples in the presence of a fraction of malicious noise.

We present polynomial-time algorithms to estimate the mean and covariance with error guarantees in terms of information-theoretic lower bounds.

This repository contains code for computing the mean of a distribution in the presence of adversarial noise. The code is written in Matlab.

Sep 10, 2024 · We present polynomial-time algorithms to estimate the mean and covariance with error guarantees in terms of information-theoretic lower bounds.

Classical robust mean estimation methods such as coordinate-wise median and geometric median have error bounds that scale with the dimension of the data [8] , ...

Duration: 55:42
Posted: Jan 24, 2017

For example, the Tukey median Tukey (1975) is a sample-efficient robust mean estimator for spherical Gaussian distributions. ... Agnostic estimation of mean and ...