overfeed.news

How AI training scales

OpenAI News

7y

Age

Published
Collected

We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training on a wide range of tasks. Since complex tasks tend to have noisier gradients, increasingly large batch sizes are likely to become useful in the future, removing one potential limit to further growth of AI systems. More broadly, these results show that…

Read the full article at openai.com

overfeed.news indexes and links. We publish a short excerpt — the full article stays at OpenAI News.

More from OpenAI News

Log in to follow this source
How AI training scales — overfeed.news