Gabriel Stechschulte

@jpchen Is a PR still in the works for the change point kernel? I have a project where this kernel could be of use and I will only develop myself...

> Hi @GStechschulte, I have a version locally but it doesn't yet support batching (and thus probably won't pass the unit tests) and I havent had the bandwidth to do...

Hey @jacobrgardner, I am currently facing the same issue as @SebastianCall (however, with my own dataset and am posting here since it is the same issue) Have either of you...

> Hey @SebastianCallh, in the coming summer months I will have time to go on a deep dive into this issue. I will keep this thread updated.

Hey @Ceyron I also apologize for the late response. I think it is resulting from the `tfp.vi.monte_carlo_variational_loss` function, and the results are different possibly because there is no PRNG /...

I ran this example locally (2019 MacBook Pro using macOS Monterey) a couple days ago and it worked fine: ```shell pyro-api=0.1.2 pyro-ppl=1.8.1 torch=1.11.0 ``` My results were in line with...

This somewhat exists in the last section of [getting started](https://bambinos.github.io/bambi/notebooks/getting_started.html#Accessing-back-end-objects). Is this what this issue is referring to? Or is a more in depth example wanted; showing how to inspect,...

Hey @zwelitunyiswa, I haven't ignored this. Things are a bit busy at work, but I will try to get to it soon. Thanks!

I have been thinking about working on this issue. However, after reviewing some of the literature on HMC, dynamic HMC, and NUTS, it is a bit unclear to me the...

> I should have named this issue "multinomial HMC", I am sorry for the confusion. It is simply HMC but where you sample the trajectory instead of building it linearly,...