Weight decay

[adamlerer]

Types of changes

• Docs change / refactoring / dependency upgrade
• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)

Motivation and Context / Related issue

We currently have the N3 regularizer implemented, but some users want unweighted weight decay (i.e. weight decay the entire dense embedding matrix). We do this on an interval to amortize the cost of the dense weight update.

How Has This Been Tested (if it applies)

It's being used in SIMBA.

Checklist

• The documentation is up-to-date with the changes I made.
• I have read the CONTRIBUTING document and completed the CLA (see CONTRIBUTING).
• All tests passed, and additional code has been covered with new tests.

[facebook-github-bot]

@adamlerer has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[facebook-github-bot]

Hi @adamlerer!

Thank you for your pull request.

We require contributors to sign our Contributor License Agreement, and yours needs attention.

You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!