Multiple Parallel chains

JakeColtman / bartpy

Bayesian Additive Regression Trees For Python

https://jakecoltman.github.io/bartpy/

MIT License

219 stars 44 forks source link

Multiple Parallel chains #29

Closed JakeColtman closed 5 years ago

JakeColtman commented 5 years ago

To assess convergence to the true distribution, it is useful to run several chains from different start points. At the moment, this requires running the model multiple times in parallel.

There are two related parts of this issue: 1) conceptually support multiple chains in the API 2) use multiprocessing of the like to parallelize

JakeColtman commented 5 years ago

Completed in pull request #30 - more work to be done on making it pretty