Timezone: »

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
Julien Launay · Iacopo Poli · François Boniface · Florent Krzakala

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1564

Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment (DFA) to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. When a larger gap between DFA and backpropagation exists, like in Transformers, we attribute this to a need to rethink common practices for large and complex architectures. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.

Author Information

Julien Launay (LightOn)
Iacopo Poli (LightOn)
François Boniface (LightOn)
Florent Krzakala (ENS Paris, Sorbonnes Université & EPFL)

More from the Same Authors