# Speed up Gaussian Process model

**URL:** <https://discourse.julialang.org/t/speed-up-gaussian-process-model/82315>\
**Category:** Probabilistic Programming\
**Tags:** turing, stheno\
**Created:** [June 6, 2022, 2:31pm UTC](https://discourse.julialang.org/t/speed-up-gaussian-process-model/82315 "2022-06-06T14:31:27Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![marius311](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/marius311/32/3953_2.png) [@marius311](https://discourse.julialang.org/u/marius311)\
**Post date:** [June 7, 2022, 12:50am UTC](https://discourse.julialang.org/t/speed-up-gaussian-process-model/82315/6 "2022-06-07T00:50:06Z")

</div>

Depending on what exactly you need, at a glance it looks like its the type of model that MUSE might be applicable to (theoretically, and also in practice since there’s a Turing interface). I gave an example [here](https://discourse.julialang.org/t/nuts-speed-is-very-slow-for-high-dimension-parameter-inference-in-turing-jl/80349/9) which gave big speedups over HMC, the [docs](https://cosmicmar.com/MuseInference.jl/latest/) are pretty good too, and show big speedups over VI as well. Please don’t hesitate to get in touch if you try it out and/or run into anything!

---

_[View the full topic](https://discourse.julialang.org/t/speed-up-gaussian-process-model/82315)._