API Reference¶
Bayes-skopt, or bask, builds on Scikit-Optimize and implements a fully Bayesian sequential optimization framework of very noise black-box functions.
bask
: module¶
Base classes¶
|
Gaussian process regressor of which the kernel hyperparameters are inferred in a fully Bayesian framework. |
|
Fully Bayesian optimization over hyper parameters. |
|
Execute a stepwise Bayesian optimization. |
Functions¶
|
Guess suitable priors for the hyperparameters of a given kernel. |
|
Output |
bask.acquisition
: Acquisition¶
User guide: See the acquisition section for further details.
Implements the predictive variance reduction search algorithm. |
|
Select points based on their mutual information with the optimum value. |
|
Select the point maximizing the expected improvement over the current optimum. |
|
Select the point with the highest expected improvement over the point with the maximum expected improvement overall. |
|
Select the point with the lowest lower confidence bound. |
|
Select the point with the lowest estimated mean. |
|
Sample a random function from the GP and select its optimum. |
|
A criterion which tries to find the region where it can reduce the global variance the most. |
|
Run a set of acquisitions functions on a given set of points. |
bask.optimizer
: Optimizer¶
User guide: See the optimizer section for further details.
|
Execute a stepwise Bayesian optimization. |
bask.utils
: Utils functions.¶
User guide: See the utils section for further details.
|
Compute the geometric median for the given array of points. |
|
Output |
|
Guess suitable priors for the hyperparameters of a given kernel. |
|
Construct a Matern kernel as default kernel to be used in the optimizer. |