When does the Tukey median work?

01/21/2020
by   Banghua Zhu, et al.
0

We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces to 1/4 for the same set of distributions. We also show that a certain projection algorithm can attain the optimal breakdown point of 1/2. Both the Tukey median estimator and the projection algorithm achieve sample complexity linear in dimension.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/01/2020

A Total Variation Denoising Method Based on Median Filter and Phase Consistency

The total variation method is widely used in image noise suppression. Ho...
research
09/17/2023

Total Variation Distance Estimation Is as Easy as Probabilistic Inference

In this paper, we establish a novel connection between total variation (...
research
06/14/2022

On Approximating Total Variation Distance

Total variation distance (TV distance) is a fundamental notion of distan...
research
02/08/2018

Statistical Learnability of Generalized Additive Models based on Total Variation Regularization

A generalized additive model (GAM, Hastie and Tibshirani (1987)) is a no...
research
09/17/2023

L^1 Estimation: On the Optimality of Linear Estimators

Consider the problem of estimating a random variable X from noisy observ...
research
05/23/2023

Statistical Indistinguishability of Learning Algorithms

When two different parties use the same learning rule on their own data,...
research
02/10/2019

The Optimal Approximation Factor in Density Estimation

Consider the following problem: given two arbitrary densities q_1,q_2 an...

Please sign up or login with your details

Forgot password? Click here to reset