In plain words: These lecture notes collect recent results on learning from data that may contain outliers or heavy noise, focusing on how reliable estimators are built and why they work. They lay out the main principles behind these tools rather than covering every development in the field.

Abstract

These notes gather recent results on robust statistical learning theory. The goal is to stress the main principles underlying the construction and theoretical analysis of these estimators rather than provide an exhaustive account on this rapidly growing field. The notes are the basis of lectures given at the conference StatMathAppli 2019.

Matthieu Lerasle
arXiv:1908.10761 · stat.ML, cs.LG, math.ST · submitted Aug 28, 2019
abstract · pdf · html