Skip to content

Rethink sampler#8

Merged
felixheptner merged 10 commits intomasterfrom
rethink_sampler
May 2, 2025
Merged

Rethink sampler#8
felixheptner merged 10 commits intomasterfrom
rethink_sampler

Conversation

@felixheptner
Copy link
Owner

No description provided.

felixheptner and others added 10 commits April 24, 2025 15:20
* Added BetaSolutionSampler which represent a beta distribution
over the Pareto Front.

* Points can optionally be projected onto the normal vector simplex,
and onto the x-axis (currently works in only 2 dimensional objective
functions)

* Removed Uniform Sampler as it can be well approximated by the Normal
sampler and represented by the new beta sampler.
* Added a diverstiy based solution sampler that calculates weights
based on crowding distances
*Removed Normal and Beta Solution Sampler and added a generic
PDF Solution Sampler, that accepts any pdf from scipy.stats
@felixheptner felixheptner merged commit 8a8bf9e into master May 2, 2025
3 checks passed
@felixheptner felixheptner deleted the rethink_sampler branch May 2, 2025 11:20
@github-actions
Copy link

github-actions bot commented May 2, 2025

⚠️ Pylint job contains errors or warnings ⚠️

Please check the report here.
(The PR will still pass the pipeline)

felixheptner added a commit that referenced this pull request Sep 23, 2025
* Add BetaSolutionSampler

* Added BetaSolutionSampler which represent a beta distribution
over the Pareto Front.

* Points can optionally be projected onto the normal vector simplex,
and onto the x-axis (currently works in only 2 dimensional objective
functions)

* Removed Uniform Sampler as it can be well approximated by the Normal
sampler and represented by the new beta sampler.

* Add DiversitySolutionSampler

* Added a diverstiy based solution sampler that calculates weights
based on crowding distances

* Change name and standard value for Normal parameters

* Add missing line at eof in sampler.py

* Refactor Solution Sampler

*Removed Normal and Beta Solution Sampler and added a generic
PDF Solution Sampler, that accepts any pdf from scipy.stats

* Fix dependencies that relied on NormalSampler

* Expose pdf_args to hypertuner

* Return to Beta solution sampler
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant