5 papers
On the robustness of minimum norm interpolators and regularized empirical risk minimizers
Geoffrey Chinot, Matthias Löffler, Sara van de Geer
This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, pote…
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…
Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems
Atsushi Nitanda, Geoffrey Chinot, Taiji Suzuki
Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks. Most studies especially focuse…
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…
Robust learning and complexity dependent bounds for regularized problems
Geoffrey Chinot
We study Regularized Empirical Risk Minimizers (RERM) and minmax Median-Of-Means (MOM) estimators where the regularization function is an even convex function. We obtain…