Skip to content

Add effective sample size estimators#1414

Open
kevinchern wants to merge 9 commits intodwavesystems:mainfrom
kevinchern:feature/ess
Open

Add effective sample size estimators#1414
kevinchern wants to merge 9 commits intodwavesystems:mainfrom
kevinchern:feature/ess

Conversation

@kevinchern
Copy link
Contributor

@kevinchern kevinchern commented Feb 19, 2026

Add effective sample size estimators based on Revisiting the Gelman-Rubin Diagnostic

@kevinchern kevinchern marked this pull request as ready for review February 23, 2026 18:07
@thisac thisac requested review from jackraymond and pau557 February 23, 2026 18:36
Copy link
Member

@randomir randomir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A few minor suggestions.

Copy link
Member

@randomir randomir left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

Co-authored-by: Radomir Stevanovic <radomir.stevanovic@gmail.com>
Copy link
Contributor

@pau557 pau557 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks good so far, but I would add more contextual elements

  • Time steps are mentioned in the definition of the x argument, but not in the text body. It should be clear what these time steps represent.
  • Similarly, what are the elements of the matrix? We know that they were generated in independent Markov chains at different time steps, but we don’t know what they are. Is it an aggregation metric?

I suggest a practical intuitive example of how this method is expected to be used within the context of dimod samplers.

And I think that it would be great to include an API that accepts dimod samplesets.

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.

4 participants