docs: fix incorrect spectral radius computation in README example#50
Open
sunnyc0206 wants to merge 3 commits intokyegomez:mainfrom
Open
docs: fix incorrect spectral radius computation in README example#50sunnyc0206 wants to merge 3 commits intokyegomez:mainfrom
sunnyc0206 wants to merge 3 commits intokyegomez:mainfrom
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR corrects the stability diagnostic shown in the README example for the recurrent block.
The current example uses A.max().item() to represent the spectral radius of matrix A, which is mathematically incorrect. Stability in the recurrent formulation is governed by the spectral radius ρ(A), defined as the maximum absolute eigenvalue of A, not its maximum element.
This update replaces the incorrect computation with the correct formulation:
rho = torch.linalg.eigvals(A).abs().max().item()
and updates the accompanying print statement accordingly.
Rationale:
The README specifies that stability requires ρ(A)<1. The previous implementation did not compute this quantity, which could lead to incorrect interpretation of model stability during experimentation or debugging.
Impact:
#51