Dan Foreman-Mackey

This is something I've been working on a little bit and I have thoughts! I'm not using starry directly, or really fitting phase curves, I've mostly been thinking about robust...

This is the numpy pin that I use: `numpy

The open pull request https://github.com/dfm/emcee/pull/376 adds this support but it's still a work in progress. You could follow that PR for updates or see if you could see how to...

There shouldn't be any problem doing this with emcee. Just be careful: if you're computing the internal expectations stochastically, that can lead to problems. You need to make sure that...

Hard to diagnose from such limited info. Are you sure that you don't have nans in your chains?

That suggests that there's some sort of under or overflow happening. Take a look at your chains to see if any parameters are especially large or small and the post...

Thanks for the report! I think it's a good suggestion to enable this behavior (it doesn't work currently because the state is entirely encoded via the backend) and I'll look...

The samples in an MCMC chain are not independent (see https://emcee.readthedocs.io/en/stable/tutorials/autocorr/ for example) so it can be redundant to store many non-independent samples. `thin=n` takes the chain and returns every...

No, that's not necessarily right and there's never going to be any "best" thin value. That can be a fine choice in some cases, but remember that the integrated autocorrelation...

That is no longer the recommended mode for serializing samples (you're looking at the docs for version 2 but using version 3). Check out the backend docs: https://emcee.readthedocs.io/en/stable/user/backends/