hyperband_n_configs

Calculates how many different configurations are sampled.

Successive Halving (Jamieson and Talwalkar (2016)
<doi:10.48550/arXiv.1502.07943>) and Hyperband (Li et al. 2018 <doi:10.48550/arXiv.1603.06560>)
optimization algorithm for the mlr3 ecosystem. The implementation in
mlr3hyperband features improved scheduling and parallelizes the evaluation
of configurations. The package includes tuners for hyperparameter
optimization in mlr3tuning and optimizers for black-box optimization in
bbotk.

Marc Becker

mlr3hyperband

Hyperband for 'mlr3'

Sebastian Gruber

Jakob Richter

Julia Moosbauer

Bernd Bischl

hyperband_n_configs function

<dl><dt>r_min</dt>
<dd>(<code>numeric(1)</code>) 
Lower bound of budget parameter.</dd>
<dt>r_max</dt>
<dd>(<code>numeric(1)</code>) 
Upper bound of budget parameter.</dd>
<dt>eta</dt>
<dd>(<code>numeric(1)</code>) 
Fraction parameter of the successive halving algorithm: With every stage the
configuration budget is increased by a factor of <code>eta</code> and only the best
<code>1/eta</code> points are used for the next stage. Non-integer values are supported,
but <code>eta</code> is not allowed to be less or equal 1.</dd></dl>

Arguments

Hyperband Configs — hyperband_n_configs

<dl>

<dt>r_min</dt>
<dd>(<code>numeric(1)</code>) 
Lower bound of budget parameter.</dd>


<dt>r_max</dt>
<dd>(<code>numeric(1)</code>) 
Upper bound of budget parameter.</dd>


<dt>eta</dt>
<dd>(<code>numeric(1)</code>) 
Fraction parameter of the successive halving algorithm: With every stage the
configuration budget is increased by a factor of <code>eta</code> and only the best
<code>1/eta</code> points are used for the next stage. Non-integer values are supported,
but <code>eta</code> is not allowed to be less or equal 1.</dd>

</dl>

hyperband_n_configs: Hyperband Configs

Description

Usage

Value

Arguments