Dmitry Balabka

@xabbuh which one?

@theArtechnology I don't think so. This fork is most up-to-date: https://github.com/ecentria/JsonApiBundle

@RuslanZavacky I see that this PR address a huge topic of JSON:API document format serialization/deserialization. It is a great job! I can't wait to use this functionality in my project....

@RuslanZavacky I realized that there no strict description of filter rules in JSONAPI spec. It is up to a developer how to implement filtering operators. I see that it might...

@karpathy I can provide some help with this. I would like to dig into this project because found it very useful.

The only difference between `fit` and `fit_partial` is that `fit` calls `_reset_state` before training. `fit_partial` is useful to collect model quality metrics during training.

I would reimplement the Cython part of the library using Numba or Jax to optimize for GPU and CPU at the same time. Jax already has experimental sparse matrix support:...

@maciejkula could you please describe the idea of "fold-in" algorithm for LightFM or provide link to some paper for inspiration? I would like to review the possibility to implement it...

@SimonCW IMO iterative training is an important feature for LightFM model which can be solved using "fold-in" approach. It would be good to keep this ticket open unless iterative training...

This one probably related to https://github.com/lyst/lightfm/issues/486