54 citations · 180 across the 26 of their papers we have counts for
25 papers · 1 filter
Optimal Change-Point Detection and Localization
Nicolas Verzelen, Magalie Fromont, Matthieu Lerasle +1
Given a times series in , with a piece-wise contant mean and independent components, the twin problems of change-point detection and change-point localizati…
On the robustness of the minimum interpolator
Geoffrey Chinot, Matthieu Lerasle
We analyse the interpolator with minimal -norm in a general high dimensional linear regression framework where where is a ran…
Aggregated Hold-Out
Guillaume Maillard, Sylvain Arlot, Matthieu Lerasle
Aggregated hold-out (Agghoo) is a method which averages learning rules selected by hold-out (that is, cross-validation with a single split). We provide the first theoretical guaran…
A quantitative Mc Diarmid's inequality for geometrically ergodic Markov chains
Antoine Havet, Matthieu Lerasle, Eric Moulines +1
We state and prove a quantitative version of the bounded difference inequality for geometrically ergodic Markov chains. Our proof uses the same martingale decomposition as \cite{MR…
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…
A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning
Joon Kwon, Guillaume Lecué, Matthieu Lerasle
Hyperparameters tuning and model selection are important steps in machine learning. Unfortunately, classical hyperparameter calibration and model selection procedures are sensitive…