Announcement
Softmax bottleneck paper planned for an October 8 presentation at COLM
The presenter also calls it the “gradient bottleneck” and says the talk is scheduled for 4:40 p.m.
TLDR
On October 5, the presenter said they planned to present a paper on the softmax, or gradient, bottleneck at COLM on October 8 at 4:40 p.m. They invited people to reach out by DM.
Combined views
3.7K
2 Sources, first seen ago
likes