LossFunctions.jl

[mihirparadkar]

I think it's worth it to move the implementations of loss functions from here to LossFunctions.jl. This package has a lot of the multivariate and ordinal losses lacking in that package, as well as functions like the M_estimator for centering and scaling, but they'd be more widely-known if they were in an explicit LossFunction package.

[madeleineudell]

That sounds like a great idea. I believe LossFunctions.jl also has particularly efficient implementations that may help with compiler optimization, so moving to their paradigm may also improve performance.

…

On Jun 24, 2017 8:48 AM, "mihirparadkar" ***@***.***> wrote: I think it's worth it to move the implementations of loss functions from here to LossFunctions.jl. This package has a lot of the multivariate and ordinal losses lacking in that package, as well as functions like the M_estimator for centering and scaling, but they'd be more widely-known if they were in an explicit LossFunction package. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#79>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAyp9Ld2jFfiLzR1uHVhmOzGOTcKZLZCks5sHS-wgaJpZM4OEW1e> .