Skip to content

We meta-learn a gray-box performance predictor on the learning curves and use it for fast hyperparameter optimization on new datasets. We empirically demonstrate that our resulting approach can quickly select an accurate pretrained model for a new dataset together with its optimal hyperparameters.

License

Notifications You must be signed in to change notification settings

automl/quicktune

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

About

We meta-learn a gray-box performance predictor on the learning curves and use it for fast hyperparameter optimization on new datasets. We empirically demonstrate that our resulting approach can quickly select an accurate pretrained model for a new dataset together with its optimal hyperparameters.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published