AcqOptimizerRandomSearch

<p>Random search acquisition function optimizer.
By default, it samples <code>100 * D^2</code> random points in the search space, where <code>D</code> is the dimension of the search space.
The point with the highest acquisition value is returned.</p>

A modern and flexible approach to Bayesian Optimization / Model
Based Optimization building on the 'bbotk' package. 'mlr3mbo' is a toolbox
providing both ready-to-use optimization algorithms as well as their fundamental
building blocks allowing for straightforward implementation of custom
algorithms. Single- and multi-objective optimization is supported as well as
mixed continuous, categorical and conditional search spaces. Moreover, using
'mlr3mbo' for hyperparameter optimization of machine learning models within the
'mlr3' ecosystem is straightforward via 'mlr3tuning'. Examples of ready-to-use
optimization algorithms include Efficient Global Optimization by Jones et al.
(1998) <doi:10.1023/A:1008306431147>, ParEGO by Knowles (2006)
<doi:10.1109/TEVC.2005.851274> and SMS-EGO by Ponweiser et al. (2008)
<doi:10.1007/978-3-540-87700-4_78>.

Marc Becker

mlr3mbo

Flexible Bayesian Optimization

Lennart Schneider

Jakob Richter

Michel Lang

Bernd Bischl

Florian Pfisterer

Martin Binder

Sebastian Fischer

Michael H. Buselli

Wessel Dankers

Carlos Fonseca

Manuel Lopez-Ibanez

Luis Paquete

AcqOptimizerRandomSearch function

<p></p><p><dl>
<dt><code>n_evals</code></dt>
<dd><p><code>integer(1)</code><br>
Number of random points to sample.
Default is <code>100 * D^2</code>, where <code>D</code> is the dimension of the search space.</p></dd></dl></p><p>

</p>

Parameters

<p><code>mlr3mbo::AcqOptimizer</code> -&gt; <code>AcqOptimizerRandomSearch</code></p>

Super class

<p><div class="r6-active-bindings"></div></p><dl>
<dt><code>print_id</code></dt>
<dd><p>(<code>character</code>)<br>
Id used when printing.</p></dd><p></p><p>
</p></dl><p></p>

Active bindings


<div class="section" id="public-methods">
<h3>Public methods</h3><p></p><p><ul>
<li><p><a href="/link/AcqOptimizerRandomSearch%24new()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::AcqOptimizerRandomSearch$new()"><code>AcqOptimizerRandomSearch$new()</code></a></p></li>
<li><p><a href="/link/AcqOptimizerRandomSearch%24optimize()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::AcqOptimizerRandomSearch$optimize()"><code>AcqOptimizerRandomSearch$optimize()</code></a></p></li>
<li><p><a href="/link/AcqOptimizerRandomSearch%24clone()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::AcqOptimizerRandomSearch$clone()"><code>AcqOptimizerRandomSearch$clone()</code></a></p></li>
</ul></p><p></p></div><p><details open><summary>Inherited methods</summary>
<ul>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="format"><a href="/link/mlr3mbo%3A%3AAcqOptimizer%24format()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::mlr3mbo::AcqOptimizer$format()"><code>mlr3mbo::AcqOptimizer$format()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="print"><a href="/link/mlr3mbo%3A%3AAcqOptimizer%24print()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::mlr3mbo::AcqOptimizer$print()"><code>mlr3mbo::AcqOptimizer$print()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="reset"><a href="/link/mlr3mbo%3A%3AAcqOptimizer%24reset()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::mlr3mbo::AcqOptimizer$reset()"><code>mlr3mbo::AcqOptimizer$reset()</code></a></span></li>
</ul>
</details></p><p><hr>
<a id="method-AcqOptimizerRandomSearch-new"></a></p><div class="section" id="method-new-">
<h3>Method <code>new()</code></h3>
<p>Creates a new instance of this <a href="https://r6.r-lib.org/reference/R6Class.html">R6</a> class.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>AcqOptimizerRandomSearch$new(acq_function = NULL)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>acq_function</code></dt>
<dd><p>(<code>NULL</code> | AcqFunction).</p></dd></dl></div></p><p>
</p><p></p>
<p></p><p></p><p><hr>
<a id="method-AcqOptimizerRandomSearch-optimize"></a></p><div class="section" id="method-optimize-">
<h3>Method <code><a href="/link/optimize()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::optimize()">optimize()</a></code></h3>
<p>Optimize the acquisition function.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>AcqOptimizerRandomSearch$optimize()</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="returns">
<h4>Returns</h4>
<p><code><a href="/link/data.table%3A%3Adata.table()?package=mlr3mbo&version=1.0.0" data-mini-rdoc="mlr3mbo::data.table::data.table()">data.table::data.table()</a></code> with 1 row per candidate.</p>
</div></p><p></p><p><hr>
<a id="method-AcqOptimizerRandomSearch-clone"></a></p><div class="section" id="method-clone-">
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>AcqOptimizerRandomSearch$clone(deep = FALSE)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd></dl></div></p><p>
</p><p></p>
<p></p><p>
</p>

Methods

Random Search Acquisition Function Optimizer — AcqOptimizerRandomSearch



<dl>
<dt><code>n_evals</code></dt>
<dd><p><code>integer(1)</code><br />
Number of random points to sample.
Default is <code>100 * D^2</code>, where <code>D</code> is the dimension of the search space.</p></dd>


</dl>


<p><div class="r6-active-bindings"></p><dl>
<dt><code>print_id</code></dt>
<dd><p>(<code>character</code>)<br />
Id used when printing.</p></dd>


</dl><p></div></p>


<div class='section' id='public-methods'>
<h3>Public methods</h3>

<ul>
<li><p><a href='#method-AcqOptimizerRandomSearch-new'><code>AcqOptimizerRandomSearch$new()</code></a></p></li>
<li><p><a href='#method-AcqOptimizerRandomSearch-optimize'><code>AcqOptimizerRandomSearch$optimize()</code></a></p></li>
<li><p><a href='#method-AcqOptimizerRandomSearch-clone'><code>AcqOptimizerRandomSearch$clone()</code></a></p></li>
</ul>

</div><p><details open><summary>Inherited methods</summary>
<ul>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="format"><a href='../../mlr3mbo/html/AcqOptimizer.html#method-AcqOptimizer-format'><code>mlr3mbo::AcqOptimizer$format()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="print"><a href='../../mlr3mbo/html/AcqOptimizer.html#method-AcqOptimizer-print'><code>mlr3mbo::AcqOptimizer$print()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mlr3mbo" data-topic="AcqOptimizer" data-id="reset"><a href='../../mlr3mbo/html/AcqOptimizer.html#method-AcqOptimizer-reset'><code>mlr3mbo::AcqOptimizer$reset()</code></a></span></li>
</ul>
</details>

<hr>
<a id="method-AcqOptimizerRandomSearch-new"></a></p><div class='section' id='method-new-'>
<h3>Method <code>new()</code></h3>
<p>Creates a new instance of this <a href='https://r6.r-lib.org/reference/R6Class.html'>R6</a> class.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>AcqOptimizerRandomSearch$new(acq_function = NULL)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>acq_function</code></dt>
<dd><p>(<code>NULL</code> | AcqFunction).</p></dd>


</dl><p></div></p>
</div>

</div><p><hr>
<a id="method-AcqOptimizerRandomSearch-optimize"></a></p><div class='section' id='method-optimize-'>
<h3>Method <code><a href='https://rdrr.io/r/stats/optimize.html'>optimize()</a></code></h3>
<p>Optimize the acquisition function.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>AcqOptimizerRandomSearch$optimize()</code></pre><p></div></p>
</div>

<div class='section' id='returns'>
<h4>Returns</h4>
<p><code><a href='https://rdrr.io/pkg/data.table/man/data.table.html'>data.table::data.table()</a></code> with 1 row per candidate.</p>
</div>

</div><p><hr>
<a id="method-AcqOptimizerRandomSearch-clone"></a></p><div class='section' id='method-clone-'>
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>AcqOptimizerRandomSearch$clone(deep = FALSE)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd>


</dl><p></div></p>
</div>

</div>


AcqOptimizerRandomSearch: Random Search Acquisition Function Optimizer

Description

Arguments

Parameters

Super class

Active bindings

Methods

Public methods

Method `new()`

Usage

Arguments

Method `optimize()`

Usage

Returns

Method `clone()`

Usage

Arguments

Examples

Description

Arguments

Parameters

Super class

Active bindings

Methods

Public methods

Method new()

Usage

Arguments

Method optimize()

Usage

Returns

Method clone()

Usage

Arguments

Examples

Method `new()`

Method `optimize()`

Method `clone()`