feat: change Lipschitz cst estimation to Jacobian method#95
Merged
franckma31 merged 2 commits intomasterfrom Feb 13, 2025
Merged
feat: change Lipschitz cst estimation to Jacobian method#95franckma31 merged 2 commits intomasterfrom
franckma31 merged 2 commits intomasterfrom
Conversation
To estimate the Lipschitz constant of a model, we now use the Jacobian method that is more robust than random perturbations (subject to numerical errors). The Jacobian method computes Jacobians for a batch of inputs and gets the max singular values of each Jacobian matrix, corresponding to the local Lipschitz constant. The function then returns the greatest Lipschitz constant estimation in the batch.
cofri
force-pushed
the
feat/model_Lipschitz_constant_estimation
branch
from
f123a14 to
dfbe47f
Compare
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
To estimate the Lipschitz constant of a model, we now use the Jacobian method that is more robust than random perturbations (subject to numerical errors).
The Jacobian method computes Jacobians for a batch of inputs and gets the max singular values of each Jacobian matrix, corresponding to the local Lipschitz constant. The function then returns the greatest Lipschitz constant estimation in the batch.