[LRNRQ] Add bam from package mgcv

[bkmontgom]

Algorithm

Faster version of gam, especially with discrete = TRUE

Package

mgcv

Supported types

• classif
• clust
• dens
• regr
• surv

I have checked that this is not already implemented in

• mlr3
• mlr3learners
• mlr3extralearners
• Other core packages (e.g. mlr3proba, mlr3keras)

Why do I think this is a useful learner?

For many datasets gam is terribly slow. bam can be orders of magnitude faster, especially with discrete = TRUE.

Further Optional Comments

This would be "easy" to implement as the call and results are nearly identical to mgcv::gam. Some of the options are different and fewer families are available.