Machine learning
多元自适应回归样条 (MARS)
多元自适应回归样条(Multivariate adaptive regression splines, MARS)由Jerome Friedman于1991年提出,是一种灵活的非参数回归方法,通过组合分段线性“铰链”函数(hinge functions)自动模拟非线性和交互作用。它通过一个前向分阶段(forward stagewise)过程构建模型,在最能发挥作用的地方添加基函数,然后修剪过度增长的模型,最终得到一种可解释的加法-交互形式,其复杂度能根据数据自动调整。
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.
来源
- Friedman, J. H. (1991). Multivariate adaptive regression splines. The Annals of Statistics, 19(1), 1–67. DOI: 10.1214/aos/1176347963 ↗
如何引用本页
ScholarGate. (2026, June 2). Multivariate Adaptive Regression Splines (MARS). ScholarGate. https://scholargate.app/zh/machine-learning/mars
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 →