Machine learning
CatBoost
CatBoost 是一种梯度提升算法，由 Yandex 的 Prokhorenkova 及其同事于 2018 年推出，它能原生处理类别变量，并使用有序目标编码来避免标签泄露。通过构建树的加性集成，并在每次迭代时置乱数据顺序，它在类别繁多的数据上通常优于 XGBoost 和 LightGBM。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+1 more
来源
- Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V. & Gulin, A. (2018). CatBoost: Unbiased Boosting with Categorical Features. In NeurIPS 2018. DOI: 10.48550/arXiv.1706.09516 ↗
如何引用本页
ScholarGate. (2026, June 1). CatBoost (Categorical Boosting). ScholarGate. https://scholargate.app/zh/machine-learning/catboost
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →