<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LightGBM on C.CUI's Log</title><link>https://cuicaihao.github.io/zh/tags/lightgbm/</link><description>Recent content in LightGBM on C.CUI's Log</description><generator>Hugo</generator><language>zh-Hans</language><lastBuildDate>Sat, 17 Oct 2026 07:00:00 +1100</lastBuildDate><atom:link href="https://cuicaihao.github.io/zh/tags/lightgbm/index.xml" rel="self" type="application/rss+xml"/><item><title>从一棵树到一片森林：树模型的数学原理、算法演进与工程实践</title><link>https://cuicaihao.github.io/zh/posts/2026-10-17-from-a-single-tree-to-a-forest-mathematical-principles-algorithmic-evolution-and-engineering-practices-of-tree-models/</link><pubDate>Sat, 17 Oct 2026 07:00:00 +1100</pubDate><guid>https://cuicaihao.github.io/zh/posts/2026-10-17-from-a-single-tree-to-a-forest-mathematical-principles-algorithmic-evolution-and-engineering-practices-of-tree-models/</guid><description>从一棵决策树出发，理解 CART、随机森林与 GBDT，再比较 XGBoost、LightGBM 和 CatBoost 的训练机制、类别特征处理，以及面对真实数据问题时的评估与选择。</description></item></channel></rss>