127 citations · 236 across the 18 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
stat.ML2022★ 2 cited
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation
Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion
Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the rol…
math.PR2022★ 1 cited
Estimation of statistics of transitions and Hill relation for Langevin dynamics
Tony Lelièvre, Mouad Ramil, Julien Reygner
In molecular dynamics, statistics of transitions, such as the mean transition time, are macroscopic observables which provide important dynamical information on the underlying micr…