Skip to content
conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Insights
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Insights
Achievements
Home
›
Keywords
›
block heterogeneity
block heterogeneity
1 paper
Explore in graph
Co-occurring keywords
· papers mentioning both
hessian spectrum
(1)
adam optimizer
(1)
learning rate
(1)
stochastic gradient descent
(1)
Papers
Why Transformers Need Adam: A Hessian Perspective
NeurIPS 2024
<
1
>