Open AkiraTOSEI opened 3 years ago
A study of Direct Feedback Alignment, which allows us to parallelize parameter updates in a variety of tasks, such as the Transformer model, Graph Conv, and recommendation, and they confirm that the results are not bad.
https://arxiv.org/abs/2006.12878
2020/06/23
Julien Launay, Iacopo Poli, François Boniface, Florent Krzakala
TL;DR
A study of Direct Feedback Alignment, which allows us to parallelize parameter updates in a variety of tasks, such as the Transformer model, Graph Conv, and recommendation, and they confirm that the results are not bad.
Why it matters:
Paper URL
https://arxiv.org/abs/2006.12878
Submission Dates(yyyy/mm/dd)
2020/06/23
Authors and institutions
Julien Launay, Iacopo Poli, François Boniface, Florent Krzakala
Methods
Results
Comments