Jan comments

Results 241 comments of

Jan

Replace `prepare_for_sbi` with separate calls to for prior and simulator in all tutorials

as discussed, we will promote using `process_prior` and `process_simulator` separately instead of using `prepare_for_sbi`, e.g., by changing it in all the tutorials: replace `simulator, prior = prepare_for_sbi(custom_simulator, custom_prior)` by ```python...

[PRE REVIEW]: NumbaCS: A fast Python package for coherent structure analysis

hi @drvinceknight thanks for inviting me here. Yes, I would be up for reviewing this.

Refactor pairplot function

Thanks @danielmk ! Two comments from my side: - I noticed in my own usage that since the update of the `pairplot` function during the last hackathon, it's quite difficult...

Refactor pairplot function

this is great! 🚀

Add NPE-PFN

I agree, it's that easy, it would be great to include NPE-PFN. We should still double check whether this is legally bulletproof.

Add NPE-PFN

@dgedon or @jsvetter , would you be up for making a PR?

Improvement of custom density interface passed to Inference classes using Protocols

@ARna06 would you have time to work on the proposed changes? Not a problem if not, but please let us know - thanks! 🙏

Improvement of custom density interface passed to Inference classes using Protocols

Note, we will take over this PR internally to finish it. I changed the base of this PR to a intermediate feature branch named `fix/protocol-for-estimator-builder` with the same state of...

Use ODE solvers/integrators to improve score matching training

This has been solved in the refactoring of NPSE and FMPE into the vector field estimators, no? It's now possible to train a NPSE and then sample with ode backend...

Getting rid of `posterior_nn`, `likelihood_nn`,...

I agree, especially the variable naming is quite confusing here and we should add support for passing a `density_estimator` as well. However, one reason for passing the builder function is...