Search⌘ K
AI Features

Another Way of Growing Trees: XGBoost's grow_policy

Explore how to use XGBoost's lossguide grow policy to control tree growth by splitting nodes with the greatest loss reduction. Understand how max_leaves affects model complexity and validation performance. Practice tuning hyperparameters to optimize gradient boosting models effectively.

Controlling tree growth in XGBoost

In addition to limiting the maximum depth of trees using a max_depth hyperparameter, there is another paradigm for controlling tree growth: finding the node where a split would result in the greatest reduction in the loss function, and splitting this node, regardless of how deep it will make the tree. This may result in a tree with one or ...