Package website: release | dev

A new R6 and much more modular implementation for single- and multi-objective Bayesian Optimization.

An overview and gentle introduction is given in this vignette.

`mlr3mbo`

is built modular relying on the following R6 classes:

`Surrogate`

: Surrogate Model`AcqFunction`

: Acquisition Function`AcqOptimizer`

: Acquisition Function Optimizer

Based on these, Bayesian Optimization loops can be written, see,
e.g., `bayesopt_ego`

for sequential single-objective BO.

`mlr3mbo`

also provides an `OptimizerMbo`

class
behaving like any other `Optimizer`

from the bbotk package as
well as a `TunerMbo`

class behaving like any other
`Tuner`

from the mlr3tuning
package.

`mlr3mbo`

uses sensible defaults for the
`Surrogate`

, `AcqFunction`

,
`AcqOptimizer`

, and even the `loop_function`

. See
`?mbo_defaults`

for more details.

Minimize `f(x) = x^2`

via sequential single-objective BO
using a GP as surrogate and EI optimized via random search as
acquisition function:

```
library(bbotk)
library(mlr3mbo)
library(mlr3learners)
set.seed(1)
= ObjectiveRFun$new(
obfun fun = function(xs) list(y1 = xs$x ^ 2),
domain = ps(x = p_dbl(lower = -10, upper = 10)),
codomain = ps(y1 = p_dbl(tags = "minimize")))
= OptimInstanceSingleCrit$new(
instance objective = obfun,
terminator = trm("evals", n_evals = 10))
= srlrn(lrn("regr.km", control = list(trace = FALSE)))
surrogate = acqf("ei")
acqfun = acqo(opt("random_search", batch_size = 100),
acqopt terminator = trm("evals", n_evals = 100))
= opt("mbo",
optimizer loop_function = bayesopt_ego,
surrogate = surrogate,
acq_function = acqfun,
acq_optimizer = acqopt)
$optimize(instance) optimizer
```

```
## x x_domain y1
## 1: 0.03897209 <list[1]> 0.001518824
```

Note that you can also use `bb_optimize`

as a
shorthand:

```
library(bbotk)
library(mlr3mbo)
library(mlr3learners)
set.seed(1)
= function(xs) list(y1 = xs$x ^ 2)
fun
= srlrn(lrn("regr.km", control = list(trace = FALSE)))
surrogate = acqf("ei")
acqfun = acqo(opt("random_search", batch_size = 100),
acqopt terminator = trm("evals", n_evals = 100))
= opt("mbo",
optimizer loop_function = bayesopt_ego,
surrogate = surrogate,
acq_function = acqfun,
acq_optimizer = acqopt)
= bb_optimize(
result
fun,method = optimizer,
lower = c(x = -10),
upper = c(x = 10),
max_evals = 10)
```

```
library(mlr3)
library(mlr3learners)
library(mlr3tuning)
library(mlr3mbo)
set.seed(1)
= tsk("pima")
task
= lrn("classif.rpart", cp = to_tune(lower = 1e-04, upper = 1, logscale = TRUE))
learner
= tune(
instance tuner = tnr("mbo"),
task = task,
learner = learner,
resampling = rsmp("holdout"),
measure = msr("classif.ce"),
term_evals = 10)
$result instance
```

```
## cp learner_param_vals x_domain classif.ce
## 1: -4.594861 <list[2]> <list[1]> 0.2109375
```