Local DP Modifier #2959
Merged
Local DP Modifier #2959
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
…client-side-fixed-clipping
panh99
previously approved these changes
Mar 6, 2024
danieljanes
reviewed
Mar 6, 2024
Address comments Co-authored-by: Daniel J. Beutel <daniel@flower.ai>
danieljanes
reviewed
Mar 7, 2024
Co-authored-by: Daniel J. Beutel <daniel@flower.ai>
Co-authored-by: Daniel J. Beutel <daniel@flower.ai>
Co-authored-by: Daniel J. Beutel <daniel@flower.ai>
Co-authored-by: Daniel J. Beutel <daniel@flower.ai>
danieljanes
reviewed
Mar 8, 2024
danieljanes
approved these changes
Mar 8, 2024
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Outdated suggestions cannot be applied.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.
Issue
Description
Local DP, where each client is responsible to perform DP on its model parameters before sending them to the server.
Related issues/PRs
Merge after #2909
Proposal
Explanation
A new modifier class
LocalDpModis implemented where the user can create an instance of the class and pass DP hyperparameters. It performs clipping on the client's model updates, and then adds noise to the model parameters.Checklist
#contributions)Changelog entry
Any other comments?