How AI training scales
- ID
- 905
- Status
- new
- Published
- 14 Dec 2018, 4:00 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/how-ai-training-scales
- Source URL
- https://openai.com/news/rss.xml
Excerpt
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 neural network training need not be considered a mysterious art, but can be rigorized and systematized.
Summary
No summary yet. It will appear after the daemon summarizes this item.