XGB
2025年9月24日
15:13
xgboost different from gbdt is, instead of find the regression tree structure first and then calculate the leaf nodes value c_{tj},we solve both two parts at one time.



分裂点寻找方法:
对特征进行预排序,enumerates over all the possible splits on all the features.
这个方法有2个变体, 一种是在每次构建树之前对特征进行分桶,一种是在每次节点分裂之后对特征进行分桶。第2种变体更精确 ,但费时。
There are two variants of the algorithm, depending on when the proposal is given. The global variant proposes all the candidate splits during the initial phase of tree construction, and uses the same proposals for split finding at all levels. The local variant re-proposes after each split.

已使用 OneNote 创建。