However, this simple conversion is not good in practice. Theoretically, we can set num_leaves = 2^(max_depth) to obtain the same number of leaves as depth-wise tree. This is the main parameter to control the complexity of the tree model. ![]() ![]() To get good results using a leaf-wise tree, these are some important parameters: However, the leaf-wise growth may be over-fitting if not used with the appropriate parameters. LightGBM uses the leaf-wise tree growth algorithm, while many other popular tools use depth-wise tree growth.Ĭompared with depth-wise growth, the leaf-wise algorithm can converge much faster. Tune Parameters for the Leaf-wise (Best-first) Tree Optuna for automated hyperparameter tuning ![]() ![]() This page contains parameters tuning guides for different scenarios.įLAML for automated hyperparameter tuning
0 Comments
Leave a Reply. |