108 citations · 126 across the 6 of their papers we have counts for
8 papers
Module-wise Training of Neural Networks via the Minimizing Movement Scheme
Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac +1
Greedy layer-wise or module-wise training of neural networks is compelling in constrained and on-device settings where memory is limited, as it circumvents a number of problems of…
Block-wise Training of Residual Networks via the Minimizing Movement Scheme
Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac +1
End-to-end backpropagation has a few shortcomings: it requires loading the entire model during training, which can be impossible in constrained settings, and suffers from three loc…
A Neural Tangent Kernel Perspective of GANs
Jean-Yves Franceschi, Emmanuel de Bézenac, Ibrahim Ayed +3
We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs). We reveal a fundamental flaw of previous analyses which, by incorrectly modeling GA…
LEADS: Learning Dynamical Systems that Generalize Across Environments
Yuan Yin, Ibrahim Ayed, Emmanuel de Bézenac +2
When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of th…
Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
Yuan Yin, Vincent Le Guen, Jérémie Dona +4
Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purel…
A Principle of Least Action for the Training of Neural Networks
Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac +1
Neural networks have been achieving high generalization performance on many tasks despite being highly over-parameterized. Since classical statistical learning theory struggles to…