Tamas K. Papp

> it does not lead to any additional maintenance burden Let's see — again, PRs are welcome. Generally I think that so much happened since 1.0 in terms of new...

What would be the advantage of having this package in ELPA/core? My perception is that it would just add bureaucratic overhead (cf #1) and imply less frequent releases (in core,...

I think a separate package, which enhances the interface, would be the best approach for now, since it would allow experimentation with the mutable interface without affecting the API defined...

> if someone would implement a non-`AbstractVector` type that would want to mimick `AbstractVector` it is ~ 1 year of relatively active use of the type to catch all cases....

I will look into it.

Apologies for the delay (I am working through a large backlog) and thanks for the ping. Conceptually, the `q` is a point in `ℝⁿ` (unconstrained), after the transformation. So you...

@ClaudMor: I am not an expert on this model family, but are you sure parameters near 1 actually make sense? For `Optim.optimize`, you actually constrain to `1`, so I am...

Incidentally, I recently removed local optimization from DynamicHMC.jl (tpapp/DynamicHMC.jl#146). It adds very little to well-behaved posteriors (the adaptation restarts multiple times anyway, so the starting point should not matter much),...

No, Cholesky is notoriously bad. No serious library I know of (in other languages) uses it. It is very easy to come up with examples like ```julia using MultivariateStats function...

I am not sure I understand you argument. Are you saying that because estimation has statistical error anyway, we might as well ignore potentially significant numerical error? I can't check...