Olivier Labayle

That would be great thank you!

> @olivierlabayle Did you want to comment on this PR? I realize you might not want to review it as it is quite long, but if you're willing and interested...

Thanks @ablaom for this simplification of the learning network definition process! My only reservations are about the symbolic access of models in the definition of the network itself. For that...

Hi there, I also face a similar problem with a Bernoulli/LogitLink model. It seems the source of the NaNs originates from the [delbeta! method](https://github.com/JuliaStats/GLM.jl/blob/0c057160d28c7dc524fd8bcafe43f7491b373f30/src/linpred.jl#L151) at least in `mul!(p.delbeta, transpose(scr), r)`....

Hi, same problem here trying to install tlverse! ```R ─ installing the package to process help pages ----------------------------------- ERROR: dependency ‘imputeMissings’ is not available for package ‘sl3’ ─ removing ‘/private/var/folders/t1/kx5d52vs4kg8v_d4hhmg193c0000gn/T/RtmpL5PveW/Rinstec9a470423cb/sl3’...

Work around: ``` curl https://cran.r-project.org/src/contrib/Archive/imputeMissings/imputeMissings_0.0.3.tar.gz -o imputeMissings.tar.gz tar -zxf imputeMissings.tar.gz R devtools::install("imputeMissings/") ```

Indeed, thanks for the pointer!

Thank you for your reply, I think I've made the situation a bit more clear now. Unless I'm missing something, I think the following code illustrates how the logloss reached...

Hi Thibaut, I'm currently using MLJLinearModels for a personnal project where I need to run millions of multinomial regressions. Unfortunately, I also encounter a performance bottleneck as noted above. I...

Witnessing another pretty serious performance issue on a dataset I'm working with, using multinomial regression. I think both scikit-learn and MLJLinearModels use LBFGS: - MLJScikitLearnInterface: around **5 secs** (mean log_loss:...