imodels-experiments icon indicating copy to clipboard operation
imodels-experiments copied to clipboard

Published 20 hours ago • verified publisher icon Yu-Group

CCP and number of leaves

Open markusloecher opened this issue 1 year ago • 0 comments

In Fig. 4A/B the CCP (cost complexity pruned) graphs are puzzling to me: CCP should protect against overfitting a lot more than shown? In particular, the "number of leaves" cannot be fixed as the graph suggests; they will be a result of the pruning?

markusloecher avatar Oct 20 '23 08:10 markusloecher