KSLCore/ksl.simopt.solvers.algorithms.bo/StationaryKernel

StationaryKernel

abstract class StationaryKernel(signalVariance: Double, lengthScales: DoubleArray) : KernelIfc(source)

Base class for stationary kernels parameterized by an output scale (signalVariance) and a per-dimension length scale (lengthScales, i.e. automatic relevance determination, ARD).

Parameters

signalVariance

the output scale (prior variance). Must be > 0.

lengthScales

the per-dimension length scales. Must be non-empty and all > 0.

Inheritors

RBFKernel

Matern52Kernel

Constructors

StationaryKernel

constructor(signalVariance: Double, lengthScales: DoubleArray)

Properties

dimension

val dimension: Int

The input dimension (number of length scales).

lengthScales

var lengthScales: DoubleArray

signalVariance

var signalVariance: Double

Functions

scaledSquaredDistance

protected fun scaledSquaredDistance(x1: DoubleArray, x2: DoubleArray): Double

The sum of squared, length-scaled coordinate differences between x1 and x2.