activity
20122022
most citedModeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

489 citations · 600 across the 8 of their papers we have counts for

collaborators
Showing 2020Show all

7 papers · 1 filter

cs.LG2020

Implicit Regularization via Neural Feature Alignment

Aristide Baratin, Thomas George, César Laurent +4

We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neura…

cs.LG202015 cited

Stochastic Hamiltonian Gradient Methods for Smooth Games

Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau +3

The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods a…

cs.LG2020

Sharp Analysis of Smoothed Bellman Error Embedding

Ahmed Touati, Pascal Vincent

The \textit{Smoothed Bellman Error Embedding} algorithm~\citep{dai2018sbeed}, known as SBEED, was proposed as a provably convergent reinforcement learning algorithm with general no…

cs.LG2020

Adversarial Example Games

Avishek Joey Bose, Gauthier Gidel, Hugo Berard +4

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of sa…

cs.LG20206 cited

Revisiting Loss Modelling for Unstructured Pruning

César Laurent, Camille Ballas, Thomas George +2

By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. I…

cs.CL2020

Do sequence-to-sequence VAEs learn global features of sentences?

Tom Bosc, Pascal Vincent

Autoregressive language models are powerful and relatively easy to train. However, these models are usually trained without explicit conditioning labels and do not offer easy ways…