-
Curious if you've had a look at the statespace work going on in statsmodels? @chadfulton
-
It'd be nice to have a language to specify directed acyclic graphs, so we can take advantage of Rao-Blackwellization/Markov blankets. Also it'd be nice to take advantage of the case when all full cond…
-
At PyData London @twiecki and I chatted about what needed to be done for a release, and @jonsedar presented a nice advanced tutorial on it.
As I understand it there's just a few things left before a r…
-
First of all, I love this package, the documentation, and especially your (@jluttine) enthusiasm and willingness to help people learn how to use it. You are a huge credit to the community, so thanks!
…
-
@karlnapf
- add `register_optimizer` method in `InferenceMethod` (base ) class
- all approximate inference methods (excluding Exact, Var_DTC, FITC, and EP) will use a build-in optimizer unless use…
-
I think it's time we start moving away from Wiki pages toward a solution like Sphinx or mkdocs. Things like #95, #96, #98 clearly motivate this. Here are some thoughts off the top of my head:
- clean,…
-
we currently default to the reparameterization gradient if the `Variational` class implements `reparam`
however, if the `Inference` class does not support reparameterization gradients (e.g. `KLpq`) t…
-
Can the theano infrastructure handle this?
https://github.com/stan-dev/stan/pull/1421
http://andrewgelman.com/2015/02/18/vb-stan-black-box-black-box-variational-bayes/
-
Hi,
Thanks for the great package. I am trying to modify your LDA model code, by using gradient methods (model.optimize()) where I collapse out p_topic and p_word during inference but I am hitting an …
-
When I run an mrd/bgplvm with an additions of kernels (for the ones we have the cross-statistics, eg linear plus bias) I get an error. I don't remember this being a problem before the release, and fro…