I will use logistic-regression-related methods like Generalized additive models and Kernel Logistic Regression, so these are due to the large sample size nearly not affected by unequal classes.

KLR seems to be coming out of nowhere: I found the name KLR to be mentioned first around 2000 (for example in "kernel logistic regression and the import vector machine", Zhu and Hastie, 2001). But they say in there it is well known and reference smoothing spline literature. My Question is: When and where was KLR first introduced and why do they always reference smoothing-splines?

Thanks, i will have a closer look at wahba's publications. Can you recommend an implementation of KLR, at best in R?

Thank you Dikran! Could you explain to me the relation of KLR und Kernel smoothing? The KLR-model is built similar to the svm [loss + penalty]-formulation and solved via gradient descent. But the same time references (e.g. in "Kernel Logistic Regression and the Import Vector Machine", Zhu and Hastie 2005) on KLR go to the smoothing-literature (e.g. "Generalized Additive Models", Hastie and Tibshirani 1990).

Hey Mariana, thanks for your answer, but we had a misunderstanding: I by "kernel methods" mean methods such as the Support vector machine using the "kernel trick", not kernel smoothing methods.