jairedc

> Is it just the order of features that is different or is it the features themselves? Since features are extracted in parallel, you never know in which order they...

Adding onto this, it seems like whenever `implicit_sampler.cpp:268` provides a `nan` value to `pt_function`, `pt_gradient` is full of `nan`. This turns `pt` into a nan as well from addition on...

Any update on this?