Haha, yes! We are working on adding support for numpyro and pymc next.

Kudos to @sethaxen.com for implementing the Pyro wrapper that makes this possible (shipped in sbi v0.25)!

And thanks to @juanitorduz.bsky.social sharing the cookie factory example—it's a great accessible example for hierarchical inference.

Everything runs in Colab 📊

Materials from my EuroSciPy talk "Pyro meets SBI" are now available: github.com/janfb/pyro-meets-sbi

I show how we can use @sbi-devs.bsky.social-trained neural likelihoods in pyro 🔥

Check it out if you need hierarchical Bayesian inference but your simulator / model has no tractable likelihood.

From hackathon to release: sbi v0.25 is here! 🎉

What happens when dozens of SBI researchers and practitioners collaborate for a week? New inference methods, new documentation, lots of new embedding networks, a bridge to pyro and a bridge between flow matching and score-based methods 🤯

1/7 🧵

Fun read of their amazing contributions to the SBI hackathon! 🥐
The SBI-Pyro bridge that @sethaxen.com built has a lot of potential I believe. I'll actually be presenting this work at @euroscipy.bsky.social this Wednesday - excited to share this with a broader audience.
euroscipy.org/talks/KCYYTF/

More great news from the SBI community! 🎉
Two projects have been accepted for Google Summer of Code under the NumFOCUS umbrella, bringing new methods and general improvements to sbi. Big thanks to @numfocus.bsky.social, GSoC and our future contributors!

Great reminder of this sunny and so productive week in March and how much I enjoy being part of this dedicated and lovely group of SBI contributors! 🤗
Big thanks to all participants & co-organizers! 🎉

🥳Great news, our JOSS paper "sbi reloaded" has been accepted! 🎉
This community lead by the fine folks of @sbi-devs.bsky.social is very welcoming and super fun to work with! I learn with every discussion I have.
paper: joss.theoj.org/papers/10.21...
review: github.com/openjournals...

We have been thinking about this for a while and now it’s here 🎉Looking forward to all the exciting SBI applications we will be discussing, and to onboarding new contributors! 🚀

It's been a blast, thanks to @sbi-devs.bsky.social ! This week's hackathon was phenomenal! 🙏 😍 The sbi hackathon welcomed about 25 people in Tübingen with contributions spanning the globe , e.g. 🇺🇸🇯🇵🇧🇪🇩🇪. Wanna see, what we did? Check out the PRs👇
github.com/sbi-dev/sbi/...

On my way to the SBI hackathon in Tübingen—on a EuroCity that’s overbooked, delayed, and mysteriously missing all reservation signs. People pacing the aisles, luggage blocking exits, a baby wailing in the distance… 🚆🔥😵‍💫

If only the German railway system were as user-friendly as the SBI package! 🥲

thanks for the response! yes, that makes sense. I was wondering how exactly you sample from the augmented posterior as this was not clear to me from reading the paper. E.g., in the SBI case (DDM example), how do you sample p(theta | x_i, x_o) given that the conditions are not iid?

Really neat idea!
I had a quick look and did not quite understand how the „augmented“ posterior is obtained or how you can sample from it to calculate the conditional ranks.
Thanks 🙏

Actually, I think this can be useful for mixed-effects models as well: you define a hierarchical prior and simulator with your fixed effects model and then train NLE on single trial data. At inference time, you then condition on x and conditions for each subject, or for multiple subjects at once.

Good question, thanks! When you train NLE on single trials, you can now run inference given a set of iid trials and additionally condition on corresp. set of varying experimental condition (without retraining). Perm. inv. nets are used in NPE settings, which usually requires retraining. Clarified?

For everyone working with trial-based i.i.d. data and varying experimental conditions - we have you covered now!
You need to train NLE only once and then can run MCMC with multiple subjects, trials and conditions, etc.
Example: sbi-dev.github.io/sbi/dev/tuto...
Reach out on GitHub for questions 🙋‍♂️

Would you mind adding me as well? I work on SBI and related methods. Thanks!

So happy to be part of this project and see it growing!
Many thanks to all contributors and users for making it possible 🚀

Hello, world! We are a community-developed toolkit that performs Bayesian inference for simulators. We support a broad range of methods (NPE, NLE, NRE, amortized and sequential), neural network architectures (flows, diffusion models), samplers, and diagnostics. Join us!

Great list! Thanks for initiating this. Can you please add me as well? I work on OSS for science, e.g., bsky.app/profile/sbi-...
Thanks!

Great, thanks for creating this! Please add me as well.