Search Results for author: Louis Fournier

Found 4 papers, 3 papers with code

Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks

no code implementations13 Mar 2024 Louis Fournier, Edouard Oyallon

Training large deep learning models requires parallelization techniques to scale.

Can Forward Gradient Match Backpropagation?

1 code implementation12 Jun 2023 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 for neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements.


Paraphrases do not explain word analogies

1 code implementation EACL 2021 Louis Fournier, Ewan Dunbar

Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on).

Word Embeddings

Analogies minus analogy test: measuring regularities in word embeddings

1 code implementation CONLL 2020 Louis Fournier, Emmanuel Dupoux, Ewan Dunbar

Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.