Seth Axen

> Its a bit of a complicated example so if that doesn't make a lot of sense; I can try and find a more minimal fail. At first glance, I...

> Exciting to see this work being done in Julia! Do you think it would make sense to include an example of how you could use the results of this...

@burtonjosh these look very nice, and I'd be happy to include them as examples! I think a new docs section "More examples" with a subpage for each would be a...

@SamuelBrand1 this line is using a deprecated syntax: https://github.com/CDCgov/Rt-without-renewal/blob/d6344cc6e451e3e6c4188e4984247f890ae60795/EpiAware/src/EpiLatentModels/utils.jl#L19, which _could_ be the issue here. Try this instead, and let me know if it works `truncated(Normal(0, prior_mean * sqrt(pi) /...

> However, switching to `AutoReverseDiff(false)` does Ah, okay. Tape compilation is only safe if during program execution the same branches of all control flow are always taken. Not certain what...

> Are all of those quantities well defined for a generic Stan model? The gradient w.r.t constrained parameters seems particularly problematic for constraints like the simplex which have a different...

To be clear, I'm just gathering information at this point. I don't have a use case for this, but the people I was talking with do.

> We don't need Jacobian-vector products for transforms anywhere in Stan, so we've never coded it. > It probably wouldn't be too hard to code all these as Jacobian-vector products...

> In this example, `lambda` is the result of applying `exp` to the (implicit) unconstrained parameter corresponding to `log(lambda)`. So the derivative propagated through `exponential_lpdf` will propagate back to the...

> I haven't seen this functionality in Turing or PyMC---is there a pointer to how they do it somewhere? Not that I'm aware of. I think that would get too...