Outlier-robust estimation of a sparse linear model using ℓ_1-penalized Huber's M-estimator
We study the problem of estimating a p-dimensional s-sparse vector in a linear model with Gaussian design and additive noise. In the case where the labels are contaminated by at most o adversarial outliers, we prove that the ℓ_1-penalized Huber's M-estimator based on n samples attains the optimal rate of convergence (s/n)^1/2 + (o/n), up to a logarithmic factor. This is proved when the proportion of contaminated samples goes to zero at least as fast as 1/(n), but we argue that constant fraction of outliers can be achieved by slightly more involved techniques.
READ FULL TEXT