23 citations · 43 across the 4 of their papers we have counts for
4 papers
Long-Tailed Learning Requires Feature Learning
Thomas Laurent, James H. von Brecht, Xavier Bresson
We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. O…
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…
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…
A recurrent neural network without chaos
Thomas Laurent, James von Brecht
We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the wor…