smac.epm.gaussian_process.gpytorch

Classes

ExactGPModel(train_X, train_y, ...)

Exact GP model serves as a backbone of the class GaussianProcessGPyTorch

GPyTorchGaussianProcess(configspace, types, ...)

class smac.epm.gaussian_process.gpytorch.ExactGPModel(train_X, train_y, base_covar_kernel, likelihood)[source]

Bases: gpytorch.models.exact_gp.ExactGP

Exact GP model serves as a backbone of the class GaussianProcessGPyTorch

forward(x)[source]

Compute the posterior mean and variance

Return type

MultivariateNormal

class smac.epm.gaussian_process.gpytorch.GPyTorchGaussianProcess(configspace, types, bounds, seed, kernel, normalize_y=True, n_opt_restarts=10, likelihood=None, instance_features=None, pca_components=None)[source]

Bases: smac.epm.gaussian_process.BaseModel

sample_functions(X_test, n_funcs=1)[source]

Samples F function values from the current posterior at the N specified test points.

Parameters

  • X_test (np.ndarray (N, D)) – Input test points

  • n_funcs (int) – The number of function values that are drawn at each test point.

Returns

function_samples – The F function values drawn at the N test points.

Return type

np.array(F, N)