Songpeng Zu

@yangsheng6810 The same issue for me. After adding your codes, it works now. Thanks a lot! Could you please merge it into the package?

@rok-cesnovar Thank you so much for showing the original codes in rstan!

@jgabry That would be great! I'm thinking about using rstan to get the importance sampling feature ... From my current experiment, I notice that sometimes, even VI can converge, the...

@rok-cesnovar In order to do the important sampling, I need the prior probabilities, the likelihoods, and the approximated probabilities (instead of ELBO). Do you have some idea about how I...

@avehtari Thank you very much for your response! I'm reading the paper you recommend. > It seems that `cmdstanr` with variational method is returning the needed `lp__` and `lp_approx__`. -...

@jgabry A quick question: which parameter in VI controls the mini-batch size? From the document, VI in stan is based on stochastic gradient ascend. Do you know the default mini-batch...

@avehtari @rok-cesnovar Thanks for your following comments. I've not implemented this part yet. But I think for me it seems straight forward: - `log_weight 0.7'). From the paper, Yao eta...

Very annoying for me too. I notice that it might stop Emacs if the buffer content is quite large. like in ESS inferior R mode, where I run an R...

Here too, OSX Sierra.

@yasuyk Thank you for your great work! I use this package every day! May I ask if this package is still maintained? Thanks! Songpeng