Skip to content
conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Insights
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Insights
Achievements
Home
›
Keywords
›
blockwise learning rate
blockwise learning rate
1 paper
Explore in graph
Co-occurring keywords
· papers mentioning both
sharpness disparity
(1)
adamw
(1)
llama
(1)
gpt2
(1)
llm pretraining
(1)
Papers
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
ICML 2025
<
1
>