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

Adding optimization using Gaussian Process #2

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Adding optimization using Gaussian Process #2

wants to merge 8 commits into from

Conversation

weslleyspereira
Copy link
Collaborator

New features:

  • GP model using ScikitLearn GaussianProcessRegression class.
  • Sampler from Mitchel (1991) that aims to improve coverage of samples.
  • Acquisition through maximization of EI.
  • Acquisition through maximization of EI avoiding clusters in the batch of samples. Adapted from Che Y, Müller J, Cheng C (2024).

More:

  • Tests for the new features.

References:

  • Mitchell, D. P. (1991). Spectrally optimal sampling for distribution ray tracing. Computer Graphics, 25, 157–164.
  • Che Y, Müller J, Cheng C. Dispersion-enhanced sequential batch sampling for adaptive contour estimation. Qual Reliab Eng Int. 2024; 40: 131–144. https://doi.org/10.1002/qre.3245

Weslley da Silva Pereira added 7 commits October 4, 2024 13:37
Encapsulate find_best()
534de86
Adds a bayesian optimization function.
450f2d2 
Also adds more functionality to the GaussianProcess class.
More tests for the bayesian optimization
17f2cfb 
- Fix inconsistencies in the MaximizeEI acquisition class
- Replace kernel() by get_kernel() in the GP class
- Use better default configuration for the GP in the bayesian optimization
- Add more tests for the bayesian optimization
Adds a notebook to show the active learning process of single-objecti…
8525c85 
…ve optimization
Replace mutable defaults
015d394
Create methods in RBFModel to make it similar to GaussianProcess
ca5c5dc
Use OptimizationResult.init() instead of initialize_surrogate().
8630f9a 
The former is preferrable for more modularity in the code.
It makes more sense now that we have multiple surrogate models.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@weslleyspereira