Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
marcinzm
on July 18, 2023
|
parent
|
context
|
favorite
| on:
A Theory on Adam Instability in Large-Scale Machin...
The whole argument is that at large scales with billions of params it doesn’t matter specifically because of those billions so giving a toy example seems to miss the point.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
