Darren’s blog was very helpful as I got started learning about bayesian inference, so it’s very neat to see Rainier appear there. (Also, he’s been a wonderful beta tester and now contributor. Thanks!)https://twitter.com/darrenjw/status/1002685644777377799 …
Seems like @seanjtaylor’s Prophet, which uses Stan, is an interesting counterpoint or exception to this.
-
-
Prophet puts some safety rails on Stan and makes it work more reliably (scaling data, sensible default hyperparams, initializing params at reasonable starting values) and makes the Stan output more user friendly. Deployment is still not a completely solved problem by any means.
-
I was under the impression that Prophet is still an interactive tool and not something that is coded into an automated production pipeline? Or is that part of the use case too? I was thinking
@avibryant meant the latter when he said "deployment." -
We have plenty of production applications where it runs without a human in the loop on a regular basis.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.