Skip to Main content Skip to Navigation
Journal articles

Robust machine learning by median-of-means : theory and practice

Guillaume Lecué 1 Matthieu Lerasle 2, 3, 4
3 SELECT - Model selection in statistical learning
LMO - Laboratoire de Mathématiques d'Orsay, Inria Saclay - Ile de France
4 CELESTE - Statistique mathématique et apprentissage
Inria Saclay - Ile de France, LMO - Laboratoire de Mathématiques d'Orsay
Abstract : We introduce new estimators for robust machine learning based on median-of-means (MOM) estimators of the mean of real valued random variables. These estimators achieve optimal rates of convergence under minimal assumptions on the dataset. The dataset may also have been corrupted by outliers on which no assumption is granted. We also analyze these new estimators with standard tools from robust statistics. In particular, we revisit the concept of breakdown point. We modify the original definition by studying the number of outliers that a dataset can contain without deteriorating the estimation properties of a given estimator. This new notion of breakdown number, that takes into account the statistical performances of the estimators, is non-asymptotic in nature and adapted for machine learning purposes. We proved that the breakdown number of our estimator is of the order of (number of observations)*(rate of convergence). For instance, the breakdown number of our estimators for the problem of estimation of a d-dimensional vector with a noise variance sigma^2 is sigma^2d and it becomes sigma^2 s log(d/s) when this vector has only s non-zero component. Beyond this breakdown point, we proved that the rate of convergence achieved by our estimator is (number of outliers) divided by (number of observation). Besides these theoretical guarantees, the major improvement brought by these new estimators is that they are easily computable in practice. In fact, basically any algorithm used to approximate the standard Empirical Risk Minimizer (or its regularized versions) has a robust version approximating our estimators. As a proof of concept, we study many algorithms for the classical LASSO estimator. A byproduct of the MOM algorithms is a measure of depth of data that can be used to detect outliers.
Document type :
Journal articles
Complete list of metadatas
Contributor : Matthieu Lerasle <>
Submitted on : Wednesday, November 14, 2018 - 8:12:37 PM
Last modification on : Thursday, July 2, 2020 - 3:16:53 AM

Links full text


  • HAL Id : hal-01923036, version 1
  • ARXIV : 1711.10306



Guillaume Lecué, Matthieu Lerasle. Robust machine learning by median-of-means : theory and practice. Annals of Statistics, Institute of Mathematical Statistics, 2019. ⟨hal-01923036⟩



Record views