MaternKernel

class baybe.kernels.basic.MaternKernel

Bases: BasicKernel

A Matern kernel using a smoothness parameter.

Public methods

__init__([nu, lengthscale_prior, ...])	Method generated by attrs for class MaternKernel.
from_dict(dictionary)	Create an object from its dictionary representation.
from_json(string)	Create an object from its JSON representation.
to_dict()	Create an object's dictionary representation.
to_factory()	Wrap the kernel in a baybe.surrogates.gaussian_process.kernel_factory.PlainKernelFactory.
to_gpytorch(*[, ard_num_dims, batch_shape, ...])	Create the gpytorch representation of the kernel.
to_json()	Create an object's JSON representation.

Public attributes and properties

nu	A smoothness parameter.
lengthscale_prior	An optional prior on the kernel lengthscale.
lengthscale_initial_value	An optional initial value for the kernel lengthscale.

__init__(nu: str | float | Fraction = 2.5, lengthscale_prior: Prior | None = None, lengthscale_initial_value=None)

Method generated by attrs for class MaternKernel.

For details on the parameters, see Public attributes and properties.

classmethod from_dict(dictionary: dict)

Create an object from its dictionary representation.

Parameters:

dictionary (dict) – The dictionary representation.

Return type:

TypeVar(_T)

Returns:

The reconstructed object.

classmethod from_json(string: str)

Create an object from its JSON representation.

Parameters:

string (str) – The JSON representation of the object.

Return type:

TypeVar(_T)

Returns:

The reconstructed object.

to_dict()

Create an object’s dictionary representation.

Return type:

dict

to_factory()

Wrap the kernel in a baybe.surrogates.gaussian_process.kernel_factory.PlainKernelFactory.

Return type:

PlainKernelFactory

to_gpytorch(*, ard_num_dims: int | None = None, batch_shape: Size | None = None, active_dims: tuple[int, ...] | None = None)

Create the gpytorch representation of the kernel.

to_json()

Create an object’s JSON representation.

Return type:

str

Returns:

The JSON representation as a string.

lengthscale_initial_value: float | None

An optional initial value for the kernel lengthscale.

lengthscale_prior: Prior | None

An optional prior on the kernel lengthscale.

nu: float

A smoothness parameter.

Only takes the values 0.5, 1.5 or 2.5. Larger values yield smoother interpolations.