# New software for sample-efficient Bayesian inference

**URL:** <https://discourse.mc-stan.org/t/new-software-for-sample-efficient-bayesian-inference/30971>\
**Category:** Publicity\
**Created:** [April 5, 2023, 4:02pm UTC](https://discourse.mc-stan.org/t/new-software-for-sample-efficient-bayesian-inference/30971 "2023-04-05T16:02:44Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![lacerbi](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/lacerbi/32/14258_2.png) [@lacerbi](https://discourse.mc-stan.org/u/lacerbi)\
**Post date:** [April 5, 2023, 4:02pm UTC](https://discourse.mc-stan.org/t/new-software-for-sample-efficient-bayesian-inference/30971/1 "2023-04-05T16:02:44Z")

</div>

Hi all, posting this as I think it might be of interest to (some) Stan users or developers.

- My group just released a new Python package (PyVBMC) for _sample-efficient_ Bayesian inference, i.e. inference with a small number of likelihood evaluations: [PyVBMC docs](https://acerbilab.github.io/pyvbmc/)
- The method runs out of the box, and we included extensive documentations and tutorials for easy accessibility: [Examples — PyVBMC](https://acerbilab.github.io/pyvbmc/examples.html)
- We have a tl;dr preprint: [[2303.09519] PyVBMC: Efficient Bayesian inference in Python](https://arxiv.org/abs/2303.09519)
- Relevant papers were published at NeurIPS in [2018](https://arxiv.org/abs/1810.05558) and [2020](https://arxiv.org/abs/2006.08655)
- More details on a [Twitter](https://twitter.com/AcerbiLuigi/status/1643549233587318784) or [Mastodon](https://mastodon.social/@AcerbiLuigi/110147657708113411) thread
- We are very interested in building interfaces between our method and other probabilistic programming languages, or methods for model visualization (e.g., ArviZ).

Please get in touch in this thread, on Twitter or via email ([luigi.acerbi@helsinki.fi](mailto:luigi.acerbi@helsinki.fi)) if you have any questions or comments!  
Thanks again for your time, and apologies for the spam.