246 citations · 1.2k across the 31 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
cs.LG2017★ 11 cited
The Multilinear Structure of ReLU Networks
Thomas Laurent, James von Brecht
We study the loss surface of neural networks equipped with a hinge loss criterion and ReLU or leaky ReLU nonlinearities. Any such network defines a piecewise multilinear form in pa…
cs.LG2017★ 8 cited
Deep linear neural networks with arbitrary loss: All local minima are global
Thomas Laurent, James von Brecht
We consider deep linear networks with arbitrary convex differentiable loss. We provide a short and elementary proof of the fact that all local minima are global minima if the hidde…
cs.LG2017★ 246 cited
Residual Gated Graph ConvNets
Xavier Bresson, Thomas Laurent
Graph-structured data such as social networks, functional brain networks, gene regulatory networks, communications networks have brought the interest in generalizing deep learning…