Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
empiko
51 days ago
|
parent
|
context
|
favorite
| on:
The Smol Training Playbook: The Secrets to Buildin...
The number of runs you can afford are not enough to perform Bayesian optimization. Count how many different options they explored in the text and take a guess how many samples you need to start modeling the hyperparameter space.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: