cox_ph_loss_sorted

Hi,

many thanks for implementing this easy to use and flexible package. I have a short question regarding the implementation of the partial likelihood function of deepsurv (`cox_ph_loss_sorted`). In the paper is a cumulative sum over the risk sets, in your implementation however this is approximated by taking the sum over all ranked samples.

Could you comment on why the approximation in `cox_ph_loss_sorted` is legit? What is the reasoning behind it?

This would help a lot! Thanks!

Start with the cox_ph_loss_sorted entry point and compare its ranked-sample sum with the cumulative risk-set formulation in the DeepSurv paper. Clarify the mathematical reasoning for the approximation in the relevant documentation or code comments, so the explanation directly answers why it is legitimate.

Written by the indexing model from the issue text.