Use absolute relative error for centroid convergence check#2
Open
uewik wants to merge 4 commits intoghimiresunil:mainfrom
Open
Use absolute relative error for centroid convergence check#2uewik wants to merge 4 commits intoghimiresunil:mainfrom
uewik wants to merge 4 commits intoghimiresunil:mainfrom
Conversation
The current convergence logic uses a raw sum of percentage changes to determine if the centroids have settled. Because the differences (curr - prev) can be negative, movements in opposite directions across different axes could mathematically cancel each other out (e.g., +5% move on X and -5% move on Y results in a sum of 0). This leads to "false convergence," where the algorithm stops prematurely even though the centroids are still moving. Changes: - Wrapped the centroid delta calculation in `np.abs()` to ensure all movement contributes positively to the tolerance check.
Merge patch-1 to main
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The current convergence logic uses a raw sum of percentage changes to determine if the centroids have settled. Because the differences (curr - prev) can be negative, movements in opposite directions across different axes could mathematically cancel each other out (e.g., +5% move on X and -5% move on Y results in a sum of 0). This leads to "false convergence," where the algorithm stops prematurely even though the centroids are still moving.
Changes:
np.abs()to ensure all movement contributes positively to the tolerance check.