NormalKernel
The Normal kernel is denoted by
\[k(y\mid x) = \mathcal{N}(y ; \mu(x) , \Sigma(x) ).\]
As with the Normal distributions, the explicit expression on the kernel depends on whether it is real or complex valued.
Types
MarkovKernels.AbstractNormalKernel
— TypeAbstractNormalKernel
Abstract type for representing Normal kernels.
MarkovKernels.NormalKernel
— TypeNormalKernel
Standard mean vector / covariance matrix parametrisation of Normal kernels.
Type aliases
const AffineNormalKernel{T} = NormalKernel{T,<:AbstractAffineMap,<:CovarianceParameter}
Constructors
MarkovKernels.NormalKernel
— MethodNormalKernel(Φ::AbstractMatrix, Σ)
Creates a NormalKernel with a linear conditional mean function given by
x ↦ Φ * x,
and conditional covariance function parameter Σ. Σ is assumed to be callable and be of compatible eltype with Φ.
MarkovKernels.NormalKernel
— MethodNormalKernel(Φ::AbstractMatrix, b::AbstractVector, Σ)
Creates a NormalKernel with an affine conditional mean function given by
x ↦ b + Φ * x,
and conditional covariance function parameter Σ. Σ is assumed to be callable and be of compatible eltype with Φ, b.
MarkovKernels.NormalKernel
— MethodNormalKernel(Φ::AbstractMatrix, b::AbstractVector, c::AbstractVector, Σ)
Creates a NormalKernel with an affine corrector conditional mean function given by
x ↦ b + Φ * (x - c),
and conditional covariance function parameter Σ. Σ is assumed to be callable and be of compatible eltype with Φ, b, c.
MarkovKernels.NormalKernel
— MethodNormalKernel(F::AbstractAffineMap, Σ::CovarianceParameter)
Creates a NormalKernel with conditional mean function F and a constant conditional covariance function parameterised by Σ.
MarkovKernels.NormalKernel
— MethodNormalKernel(F::AbstractAffineMap, Σ::AbstractMatrix)
Creates a NormalKernel with conditional mean function F and a constant conditional covariance function Σ if Σ is Symmetric / Hermitian. Throws domain error otherwise.
Basics
Statistics.mean
— Methodmean(K::AbstractNormalKernel)
Computes the conditonal mean function of the Normal kernel K. That is, the output is callable.
Statistics.cov
— Methodmean(K::AbstractNormalKernel)
Computes the conditonal covariance matrix function of the Normal kernel K. That is, the output is callable.
MarkovKernels.covp
— Methodcovp(K::AbstractNormalKernel)
Returns the internal representation of the conditonal covariance matrix of the Normal kernel K. For computing the actual conditional covariance matrix, use cov.
Conditioning and sampling
MarkovKernels.condition
— Methodcondition(K::AbstractNormalKernel, x)
Returns a Normal distribution corresponding to K evaluated at x.
Base.rand
— Methodrand(RNG::AbstractRNG, K::AbstractNormalKernel, x::AbstractVector)
Computes a random vector conditionally on x with respect the the Normal kernel K using the random number generator RNG.
Base.rand
— Methodrand(K::AbstractNormalKernel, x::AbstractVector)
Computes a random vector conditionally on x with respect the the Normal kernel K using the random number generator Random.GLOBAL_RNG.