Some recent contributions to robust inference are presented. Firstly, the classical problem of robust M-estimation of a location parameter is revisited using an optimal transport approach - with specifically designed Wasserstein-type distances - that reduces robustness to a continuity property. Secondly, a procedure of estimation of the distance function to a compact set is described, using union of balls. This methodology originates in the field of topological inference and offers as a byproduct a robust clustering method. Thirdly, a robust Lloyd-type algorithm for clustering is constructed, using a bootstrap variant of the median-of-means strategy. This algorithm comes with a robust initialization.
@article{EP_2023_74_a8,
author = {Claire Brecheteau and Edouard Genetay and Timothee Mathieu and Adrien Saumard},
title = {Topics in robust statistical learning},
journal = {ESAIM. Proceedings},
pages = {119--136},
year = {2023},
volume = {74},
doi = {10.1051/proc/202374119},
language = {en},
url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/202374119/}
}
TY - JOUR
AU - Claire Brecheteau
AU - Edouard Genetay
AU - Timothee Mathieu
AU - Adrien Saumard
TI - Topics in robust statistical learning
JO - ESAIM. Proceedings
PY - 2023
SP - 119
EP - 136
VL - 74
UR - http://geodesic.mathdoc.fr/articles/10.1051/proc/202374119/
DO - 10.1051/proc/202374119
LA - en
ID - EP_2023_74_a8
ER -