Fix missing square in proximal term of FedProx baseline #2210
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
|
I've re-run the experiments. I'll update the figure shown at the bottom of the readme |
danieljanes
requested changes
Aug 31, 2023
danieljanes
approved these changes
Sep 19, 2023
tanertopal
added a commit
that referenced
this pull request
Sep 22, 2023
* 'main' of github.com:adap/flower: Fix default contiguous value in IidPartitioner (#2406) Update FDS docs index (#2337) Add TensorFlow integration tests with FDS (#2350) Add paths specification to CI triggers for FDS (#2399) Add FDS how-to guides (#2332) Add Flower Datasets tests as GitHub workflow (#2345) Fix the reference API documentation (#2397) Add FDS tutorial docs (#2375) Update tutorial-series-what-is-federated-learning.ipynb (#2396) Fix missing square in proximal term of FedProx baseline (#2210)
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Outdated suggestions cannot be applied.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
The original FedProx paper describes the proximal term as$\frac{\mu}{2} || \omega - \omega_t ||^2$ , but the current implementation sets it as $\frac{\mu}{2} || \omega_ - \omega_{t} ||$ .
Related issues/PRs
N/A
Proposal
Explanation
Add
torch.squareto the proximal term.Checklist
#contributions)Any other comments?
N/A