.cat() / .stack() distributions (e.g. Normal distribution)

[tjoseph]

Hi,
thank you for asking. What I want to accomplish has nothing to do with distributions as such. Similar as I can for example input a batch of images in a CNN via looping over the images or via just concatenating the images in the batch dimension and inputing the whole batch, I want to concatenate my distributions and calculate the log prob. So coming back to the example I gave

@tom

log_prob would split the vector, take the log_prob of d1 and d2 and return the sum.

This is wrong. I want two log_probs, one for each event, since I am only talking about concatenation in the batch dimension!