Vincent Wieland comments

Results 5 comments of


                                            Vincent Wieland

Missing feature: Multivariate normal distribution with a different covariance matrix for each particle

Thanks for opening this issue. I got one question left about the above `Generalized_MV_Normal` class as implemented above, especially how to use it for an example as in issue #54....

Restricting sampling of parameters

Thanks for your response. It isn't clear to me how I could give the proposal covariance for the simulation of the new $\theta^p$. But unless this it is well explaind...

NaN gradient occurring in `SpecialFunctions.gamma`, when using float arguments.

@gdalle This is the issue.

Event assignment not working

Hey, @paulflang thanks for your response and the fix. Sorry, for not trying it earlier.. It does work now with your fix.

Easy switching between likelihood and posterior

Agreed, one could maybe add a flag or method to the `objective`, to distinguish different kind of objectives. Additionally, it seems like that naming and comments in some example notebooks...