hyperoptax.kernels

hyperoptax.kernels#

Functions

cdist(x, y)

Pairwise Euclidean distance (cdist) between two 2-D arrays.

Classes

BaseKernel()

Abstract base class for positive-definite kernels.

Matern([length_scale, nu])

Matern kernel family.

RBF([length_scale])

Radial basis function (RBF) / squared-exponential kernel.
hyperoptax.kernels.cdist(x, y)[source]#

Pairwise Euclidean distance (cdist) between two 2-D arrays.

Parameters:

  • x (jax.Array) – Arrays with shape (N, D) and (M, D), respectively.

  • y (jax.Array) – Arrays with shape (N, D) and (M, D), respectively.

Returns:

A distance matrix of shape (N, M).

Return type:

jax.Array

class hyperoptax.kernels.BaseKernel[source]#

Abstract base class for positive-definite kernels.

class hyperoptax.kernels.RBF(length_scale=1.0)[source]#

Radial basis function (RBF) / squared-exponential kernel.

Parameters:

length_scale (float)

__init__(length_scale=1.0)[source]#
Parameters:

length_scale (float)

class hyperoptax.kernels.Matern(length_scale=1.0, nu=2.5)[source]#

Matern kernel family.

Parameters:

  • length_scale (float, default = 1.0) – Characteristic length scale.

  • nu (float, default = 2.5) – Controls smoothness (nu ∈ {0.5, 1.5, 2.5, ∞}).

__init__(length_scale=1.0, nu=2.5)[source]#
Parameters:
Contents