Probably typo in Chapter 7 Xgboost

shokru / mlfactor.github.io

Website dedicated to a book on machine learning for factor investing

200 stars 95 forks source link

Probably typo in Chapter 7 Xgboost #1

Open gelotran opened 4 years ago

gelotran commented 4 years ago

Hi,

Can you check the formula in the part 7.4.3 Xgboost? I think there may be a typo there.

Then the formula 7.5 has to be adjusted accordingly.

Best, Vu Tran

shokru commented 4 years ago

Thanks for the feedback! I've checked again, and it seems ok to me, given the 2 factor in front of the sum...

gelotran commented 4 years ago

Hi,

Thank for feedback. I take a comparison with XGBoost website.

It seems that inside each tree leaf, we sum all the Hessian values but not a summation of \lamda.

Btw, your book is great for an R user working with Portfolio ML. I enjoy reading it a lot.

shokru commented 4 years ago

True, but I prefer to take the simpler case when the loss is quadratic (easier to follow I find). And for a quadratic loss, the Hessian is constant. That's why I get differences w.r.t to the original derivation with "2" factors at some places. Thanks for the feedback again: don't hesitate because we really want to continuously improve the book.

gelotran commented 4 years ago

You're welcome. Thank for clarification

It's actually a good book. I hope that you can continue to work on it and looking to see further work from you.