This post was published in 2021-10-20. Obviously, expired content is less useful to users if it has already pasted its expiration date.
主要内容:generalized linear regression,Laplace approximation,不对称损失函数
Linear regression, Logistic regression, Generalized Linear Models (GLM) 三者的关系
🔗 [glms.pdf] http://www.cs.columbia.edu/~blei/fogm/2016F/doc/glms.pdf
🔗 [Generalized linear model - Wikipedia] https://en.wikipedia.org/wiki/Generalized_linear_model
Link function & canonical link function (GLM)
🔗 [广义线性模型中, 联系函数(link function) 的作用是不是就是将不是正态分布的Y转换成正态分布? - 知乎] https://www.zhihu.com/question/28469421
🔗 [Generalized linear model - Wikipedia] https://en.wikipedia.org/wiki/Generalized_linear_model#Link_function
ordinal regression
Poisson regression
Laplace approximation
🔗 [拉普拉斯近似与贝叶斯逻辑回归——PRML第四章(3) | Rosen] http://rosen.xyz/2018/05/15/%E6%8B%89%E6%99%AE%E6%8B%89%E6%96%AF%E8%BF%91%E4%BC%BC%E4%B8%8E%E8%B4%9D%E5%8F%B6%E6%96%AF%E9%80%BB%E8%BE%91%E5%9B%9E%E5%BD%92/
不对称损失函数
典型例题:🔗 [1. Best classification when your losses are | Chegg.com] https://www.chegg.com/homework-help/questions-and-answers/1-best-classification-losses-asymmetric-consider-two-class-0-1-classification-problem-saw--q67492622
🔗 [代价敏感学习初探 - 有偏损失函数设计 - 郑瀚Andrew.Hann - 博客园] https://www.cnblogs.com/LittleHann/p/10587512.html#_label1