Extend varinfo to include other normalized variants. #39
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
This PR would be useful to me, what prevented it from being merged? The same authors that @jpfairbanks cites have since published a follow-up paper, which brought me to this PR. |
|
@pcjentsch I guess it was a lack of maintainers resources :( Unfortunately, the PR was submitted quite long time ag, and the codebase has changed since. To the level that there are merge conflicts, and it cannot be merged automatically. If @jpfairbanks would be so kind to review and rebase his work, I would be happy to review it. Alternatively ‐ if he would be ok with that - you can fork this PR and submit an updated version. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Variation of information can be normalized in different ways based on the properties of the application.
I added a symbol argument to specify this normalization to the
varinfofunction and set the default to the previous behavior. I also put the computation ofI, H1, H2into a functioninformationso that it could be reused in the future. This is a nonbreaking change.If there is a better way to do it, let me know and I can change the pull request. I think this is the least disruptive change possible. I added tests and documentation to match what was there.
The paper cited is here
http://jmlr.csail.mit.edu/papers/volume11/vinh10a/vinh10a.pdf