Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add a sampling layers to structure choice parameters #1065

Merged
merged 14 commits into from
Mar 4, 2021
Merged

Add a sampling layers to structure choice parameters #1065

merged 14 commits into from
Mar 4, 2021

Conversation

jrapin
Copy link
Contributor

@jrapin jrapin commented Mar 2, 2021

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

How Has This Been Tested (if it applies)

Checklist

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

@facebook-github-bot facebook-github-bot added the CLA Signed Do not delete this pull request or issue due to inactivity. label Mar 2, 2021
@jrapin jrapin self-assigned this Mar 2, 2021
@jrapin jrapin changed the title [WIP] Add a sampling layers to structure choice parameters Add a sampling layers to structure choice parameters Mar 3, 2021
jrapin
jrapin commented Mar 3, 2021
View reviewed changes
nevergrad/optimization/test_optimizerlib.py
Comment on lines +643 to +644
(None, 3, 1, False, 1000, ["CMA", "OnePlusOne"]),
(None, 3, 20, False, 1000, ["MetaModel", "OnePlusOne"]),
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@teytaud there's an interesting change here:
before this PR, the splitoptimizer was not able to figure out that the Array representing the softmax weights introduced noise. Now it does, so it changes from CMA/Metamodel to OnePlusOne. Does it make sense?

@jrapin jrapin added Type: Breaking changes Breaking changes to the API, to be notified in changelogs and removed Status: In Progess labels Mar 3, 2021
@jrapin jrapin requested a review from teytaud March 4, 2021 08:39
@jrapin jrapin merged commit eff62c2 into facebookresearch:master Mar 4, 2021
@jrapin jrapin deleted the sampling_layer branch March 4, 2021 11:34
@dependabot dependabot bot mentioned this pull request Mar 17, 2021
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@teytaud teytaud Awaiting requested review from teytaud

Assignees

@jrapin jrapin

Labels
CLA Signed Do not delete this pull request or issue due to inactivity. Difficulty: High Priority: Medium Type: Breaking changes Breaking changes to the API, to be notified in changelogs Type: Enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@jrapin @facebook-github-bot