50 citations · 296 across the 22 of their papers we have counts for
27 papers
Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
Jules Depersin, Guillaume Lecué
We consider the problem of robust mean and location estimation w.r.t. any pseudo-norm of the form where is any symmetric subs…
On the robustness to adversarial corruption and to heavy-tailed data of the Stahel-Donoho median of means
Jules Depersin, Guillaume Lecué
We consider median of means (MOM) versions of the Stahel-Donoho outlyingness (SDO) [stahel 1981, donoho 1982] and of Median Absolute Deviation (MAD) functions to construct subgauss…
Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature
Stéphane Chrétien, Mihai Cucuringu, Guillaume Lecué +1
Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as…
Robust subgaussian estimation of a mean vector in nearly linear time
Jules Depersin, Guillaume Lecué
We construct an algorithm, running in time , which is robust to outliers and heavy-tailed data and which achieves the subgaussian rate from [Lugosi,…
Robust high dimensional learning for Lipschitz and convex losses
Geoffrey Chinot, Guillaume Lecué, Matthieu Lerasle
We establish risk bounds for Regularized Empirical Risk Minimizers (RERM) when the loss is Lipschitz and convex and the regularization function is a norm. In a first part, we obtai…
Minimax regularization
Raphaël Deswarte, Guillaume Lecué
Classical approach to regularization is to design norms enhancing smoothness or sparsity and then to use this norm or some power of this norm as a regularization function. The choi…