TunerAsync: Class for Asynchronous Tuning Algorithms

TunerAsyncR Documentation

Class for Asynchronous Tuning Algorithms

Description

The TunerAsync implements the asynchronous optimization algorithm.

Details

TunerAsync is an abstract base class that implements the base functionality each asynchronous tuner must provide.

Resources

There are several sections about hyperparameter optimization in the mlr3book.

The gallery features a collection of case studies and demos about optimization.

The cheatsheet summarizes the most important functions of mlr3tuning.

Super class

mlr3tuning::Tuner -> TunerAsync

Methods

Public methods

Inherited methods

Method optimize()

Performs the tuning on a TuningInstanceAsyncSingleCrit or TuningInstanceAsyncMultiCrit until termination. The single evaluations will be written into the ArchiveAsyncTuning that resides in the TuningInstanceAsyncSingleCrit/TuningInstanceAsyncMultiCrit. The result will be written into the instance object.

Usage
TunerAsync$optimize(inst)
Arguments
inst

(TuningInstanceAsyncSingleCrit | TuningInstanceAsyncMultiCrit).

Returns

data.table::data.table()


Method clone()

The objects of this class are cloneable with this method.

Usage
TunerAsync$clone(deep = FALSE)
Arguments
deep

Whether to make a deep clone.


mlr-org/mlr3tuning documentation built on April 14, 2025, 1 a.m.