activity
20192022
most citedPrincipled Training of Neural Networks with Direct Feedback Alignment

26 citations · 76 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CL20226 cited

What Language Model to Train if You Have One Million GPU Hours?

Teven Le Scao, Thomas Wang, Daniel Hesslow +16

The crystallization of modeling methods around the Transformer architecture has been a boon for practitioners. Simple, well-motivated architectural variations can transfer across t…

cs.LG20223 cited

Scaling Laws Beyond Backpropagation

Matthew J. Filipovich, Alessandro Cappelli, Daniel Hesslow +1

Alternatives to backpropagation have long been studied to better understand how biological brains may learn. Recently, they have also garnered interest as a way to train neural net…

cs.CL202223 cited

What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?

Thomas Wang, Adam Roberts, Daniel Hesslow +5

Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly traine…

stat.ML20211 cited

Is the Number of Trainable Parameters All That Actually Matters?

Amélie Chatelain, Amine Djeghri, Daniel Hesslow +2

Recent work has identified simple empirical scaling laws for language models, linking compute budget, dataset size, model size, and autoregressive modeling loss. The validity of th…

cs.CV20211 cited

ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients

Alessandro Cappelli, Julien Launay, Laurent Meunier +2

Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent. Here we introduce ROPUST, a remarkably simple and ef…

cs.LG202010 cited

Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment

Julien Launay, Iacopo Poli, Kilian Müller +5

The scaling hypothesis motivates the expansion of models past trillions of parameters as a path towards better performance. Recent significant developments, such as GPT-3, have bee…