IMSPE

Performs Gaussian process regression with heteroskedastic noise following the model by Binois, M., Gramacy, R., Ludkovski, M. (2016) <doi:10.48550/arXiv.1611.05902>, with implementation details in Binois, M. & Gramacy, R. B. (2021) <doi:10.18637/jss.v098.i13>. The input dependent noise is modeled as another Gaussian process. Replicated observations are encouraged as they yield computational savings. Sequential design procedures based on the integrated mean square prediction error and lookahead heuristics are provided, and notably fast update functions when adding new observations.

Mickael Binois

hetGP

Heteroskedastic Gaussian Process Modeling and Design under
Replication

IMSPE function

<dl><dt>X</dt>
<dd><code>hetGP</code> or <code>homGP</code> model. Alternatively, one can provide a matrix of unique designs considered</dd>
<dt>theta</dt>
<dd>lengthscales</dd>
<dt>Lambda</dt>
<dd>diagonal matrix for the noise</dd>
<dt>mult</dt>
<dd>number of replicates at each design</dd>
<dt>covtype</dt>
<dd>either "Gaussian", "Matern3_2" or "Matern5_2"</dd>
<dt>nu</dt>
<dd>variance parameter</dd>
<dt>eps</dt>
<dd>numerical nugget</dd></dl>

Arguments

Integrated Mean Square Prediction Error — IMSPE

<dl>

<dt>X</dt>
<dd><code>hetGP</code> or <code>homGP</code> model. Alternatively, one can provide a matrix of unique designs considered</dd>


<dt>theta</dt>
<dd>lengthscales</dd>


<dt>Lambda</dt>
<dd>diagonal matrix for the noise</dd>


<dt>mult</dt>
<dd>number of replicates at each design</dd>


<dt>covtype</dt>
<dd>either "Gaussian", "Matern3_2" or "Matern5_2"</dd>


<dt>nu</dt>
<dd>variance parameter</dd>


<dt>eps</dt>
<dd>numerical nugget</dd>

</dl>

IMSPE: Integrated Mean Square Prediction Error

Description

Usage

Arguments

Details