logLikelihoodFun.NoiseKriging

logLikelihoodFun,NoiseKriging,NoiseKriging-method

&lt;-

function(x)

(sin(12

cos(7

0.7)

set.seed(123)

as.matrix(runif(10))

f(X)

X/10

*rnorm(nrow(X))

NoiseKriging(y,

(X/10)^2,

kernel

"matern3_2")

print(k)

theta0

k$theta()

ll_sigma2

function(sigma2)

logLikelihoodFun(k,

cbind(theta0,sigma2))$logLikelihood

seq(from

0.001,

length.out

101)

plot(s2,

Vectorize(ll_sigma2)(s2),

type

'l')

abline(v

k$sigma2(),

"blue")

sigma20

k$sigma2()

ll_theta

function(theta)

cbind(theta,sigma20))$logLikelihood

plot(t,

Vectorize(ll_theta)(t),

k$theta(),

function(theta_sigma2)

theta_sigma2)$logLikelihood

contour(t,s2,matrix(ncol=length(s2),ll(expand.grid(t,s2))),xlab="theta",ylab="sigma2")

points(k$theta(),k$sigma2(),col='blue')

Compute Log-Likelihood of NoiseKriging Model

Interface to 'libKriging' 'C++' library <https://github.com/libKriging> that should
provide most standard Kriging / Gaussian process regression features
(like in 'DiceKriging', 'kergp' or 'RobustGaSP' packages).
'libKriging' relies on Armadillo linear algebra library (Apache 2 license) by Conrad Sanderson,
'lbfgsb_cpp' is a 'C++' port around 'lbfgsb' library (BSD-3 license) by
Ciyou Zhu, Richard Byrd, Jorge Nocedal and Jose Luis Morales used for hyperparameters optimization,
and HDF5 features coming from HDF Group (see HDF5_LICENSE file)
possibly provided by Rhdf5lib by Mike Smith (Artistic-2.0 license).

Yann Richet

rlibkriging

Kriging Models using the 'libKriging' Library

Pascal Havé

Yves Deville

Conrad Sanderson

Ciyou Zhu

Richard Byrd

Jorge Nocedal

Jose Luis Morales

Mike Smith

logLikelihoodFun.NoiseKriging function

<dl><dt>object</dt>
<dd>An S3 NoiseKriging object.</dd>
<dt>theta_sigma2</dt>
<dd>A numeric vector of (positive) range parameters and variance at
which the log-likelihood will be evaluated.</dd>
<dt>grad</dt>
<dd>Logical. Should the function return the gradient?</dd>
<dt>bench</dt>
<dd>Logical. Should the function display benchmarking output</dd>
<dt>...</dt>
<dd>Not used.</dd></dl>

Arguments

Yann Richet <a href="/link/yann.richet%40irsn.fr?package=rlibkriging&version=0.8-0.1" data-mini-rdoc="rlibkriging::yann.richet@irsn.fr">yann.richet@irsn.fr</a>

Author

Compute Log-Likelihood of NoiseKriging Model — logLikelihoodFun.NoiseKriging

<dl>

<dt>object</dt>
<dd>An S3 NoiseKriging object.</dd>


<dt>theta_sigma2</dt>
<dd>A numeric vector of (positive) range parameters and variance at
which the log-likelihood will be evaluated.</dd>


<dt>grad</dt>
<dd>Logical. Should the function return the gradient?</dd>


<dt>bench</dt>
<dd>Logical. Should the function display benchmarking output</dd>


<dt>...</dt>
<dd>Not used.</dd>

</dl>

Yann Richet <a href='mailto:yann.richet@irsn.fr'>yann.richet@irsn.fr</a>

Compute Log-Likelihood of NoiseKriging Model

logLikelihoodFun.NoiseKriging: Compute Log-Likelihood of NoiseKriging Model

Description

Usage

Value

Arguments

Author