Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Gibbs Sampling #607

Merged
merged 8 commits into from
Apr 14, 2017
Merged

Gibbs Sampling #607

merged 8 commits into from
Apr 14, 2017

Conversation

dustinvtran
Copy link
Member

@dustinvtran dustinvtran commented Apr 14, 2017

With ed.complete_conditional, users can build their own Gibbs samplers (see #588). There is total flexibility with the scan order, blocked/collapsed versions, and many more. ed.Gibbs is basically a lightweight wrapper—building and sampling from the complete conditionals for you—in the style of other Monte Carlo inference classes.

todo

  • support various scan orders
  • support blocked
  • support collapsed (must pass in your own conditionals)
  • test
  • gibbs sampling tutorial (will be done in a future PR)

@dustinvtran dustinvtran force-pushed the feature/gibbs branch 3 times, most recently from 6423993 to d6fbeee Compare April 14, 2017 05:52
@dustinvtran dustinvtran changed the title [WIP] Gibbs Sampling Gibbs Sampling Apr 14, 2017
@dustinvtran dustinvtran force-pushed the feature/gibbs branch 2 times, most recently from 9131dd3 to 92c5d2a Compare April 14, 2017 16:38
@dustinvtran dustinvtran merged commit 973e38d into master Apr 14, 2017
@dustinvtran dustinvtran deleted the feature/gibbs branch April 14, 2017 20:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant