Edouard Oyallon

Alumni

Site web

Google Scholar

Publications

Can Forward Gradient Match Backpropagation?

Louis Fournier

Stéphane Rivaud

Eugene Belilovsky

Michael Eickenberg

Edouard Oyallon

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable fo… (voir plus)r neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements. The cost is the requirement to guess the step direction, which is hard in high dimensions. While current solutions rely on weighted averages over isotropic guess vector distributions, we propose to strongly bias our gradient guesses in directions that are much more promising, such as feedback obtained from small, local auxiliary networks. For a standard computer vision neural network, we conduct a rigorous study systematically covering a variety of combinations of gradient targets and gradient guesses, including those previously presented in the literature. We find that using gradients obtained from a local loss as a candidate direction drastically improves on random noise in Forward Gradient methods.

2023-07-24

International Conference on Machine Learning (Accept (Poster))

doi.org

proceedings.mlr.press

Preventing Dimensional Collapse in Contrastive Local Learning with Subsampling

Louis Fournier

Adeetya Patel

Michael Eickenberg

Edouard Oyallon

Eugene Belilovsky

2010-12-31

International Conference on Computational Intelligence, Modelling and Simulation (publié)