2 citations · 2 across the 1 of their papers we have counts for
3 papers · 1 filter
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its su…
Penalising the biases in norm regularisation enforces sparsity
Etienne Boursier, Nicolas Flammarion
Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between regularising parameters' norm and ob…
A survey on multi-player bandits
Etienne Boursier, Vianney Perchet
Due mostly to its application to cognitive radio networks, multiplayer bandits gained a lot of interest in the last decade. A considerable progress has been made on its theoretical…