Scott Linderman

Hey Max! This is a great suggestion, thanks! I'm frantically working toward a deadline right now so the code is undergoing heavy modifications. Once things have stabilized I'll put this...

`DiagonalRegression` is relatively new and may not be in the latest version on pypi. @mattjj can you look into updating the release version? Eliot, in the meantime please do the...

Glad that it's running now! Perhaps the easier way to get this is to look in `model.states_list`, which contains a list of `_SLDSStates` objects, one for each dataset you've added...

Hi Eliot, I do have those examples, but I'm tied up with NIPS submissions this week. I'll get them to you next week though! Best, Scott On Sun, May 14,...

Hi Kunal, please try cloning the latest from github and installing from source (`cd pylds; pip install -e .`). On Wed, Nov 18, 2020 at 5:26 PM Kunal Menda wrote:...

I’d do the same with dependencies PyBasicbayes, PyHSMM, Pylds, etc. you can see it’s breaking during the PyHSMM install. Best, Scott > On Nov 18, 2020, at 5:36 PM, Kunal...

Hi @hedgy123, thanks for your feedback! I've been doing a bunch of work that addresses various aspects of your problem. The latest versions of PySLDS support input driven dynamics and...

Sorry about that @hedgy123 -- I've been doing all my testing in python3.5. Not sure why yours crashed on joblib though. Mine would only give a runtime error if `_joblib_resample_states`...

Hi Natalia, I think the only reason is laziness on our part. It's very easy to sample predictions forward in time using the Markovian assumptions of the SLDS. I'll leave...

I made `pypolyagamma` optional in https://github.com/mattjj/pyslds/commit/99677eed7c01649caf75f5e2ace6a8e6ad036147. I followed the same design pattern that we used in `pylds`, namely, using `*CountSLDS` to cordon off the Pólya-gamma code. The README still needs...