Peter Thestrup Waade

Hey @gdalle Thank you for your thoughtful response, it's appreciated! A package extension is a good idea, I'll have a look at that. I don't know if it satisfies Turing's...

I realised (feeling a little foolish) that it works fine when just entering x as a matrix instead of a vector of vectors. This works: ``` model = m1([[1. 1....

(The vector of vectors solution would also be more flexible, since it wouldn't require all the vectors to be the same length, so perhaps this would be nice to support...

Sorry for the many messages: I just realised it of course should have been: ``` model = m1([1. 1. 1. ; 1. 1. 1.]) sample(model, NUTS(), 1000) ``` Without wrapping...

Hey mhauru ! Thank you - for a quick and comprehensive answer :) I'm aware that initialising Bar inside the model would both avoid the object being updated every time...

Hey @mhauru my apologies for the long response time here - and thanks again for your responses. I'll adapt my package to initialize the structures in the model, but keep...

@itsdfish wonderful news - I will try it out as soon as I get the chance :) Thank you, excited to use this more! I don't have any immediate use-cases...

Also, I'm assuming that allowing DualNumbers in the sample() call would be very tiresome, and I have no idea if ForwardDiff() and ReverseDiff() would be able to differentiate it even...

I suppose I don't have a specific question here, so treat this issue as an open discussion and statement of intent and feel free to close it when you want...

(and the autocorrelation bit here is not well-implemented I think, I mostly wanted to give an example of inferring a parameter of the subject's generative model).