mlr3book paradox vignette implementation

book/_quarto.yml

@@ -40,11 +40,12 @@ book:
     - part: "Advanced Topics"
       chapters:
       - chapters/chapter10/advanced_technical_aspects_of_mlr3.qmd
-      - chapters/chapter11/large-scale_benchmarking.qmd
-      - chapters/chapter12/model_interpretation.qmd
-      - chapters/chapter13/beyond_regression_and_classification.qmd
-      - chapters/chapter14/algorithmic_fairness.qmd
-      - chapters/chapter15/predsets_valid_inttune.qmd
+      - chapters/chapter11/advanced_hyperparameter_specification_using_paradox.qmd
+      - chapters/chapter12/large-scale_benchmarking.qmd
+      - chapters/chapter13/model_interpretation.qmd
+      - chapters/chapter14/beyond_regression_and_classification.qmd
+      - chapters/chapter15/algorithmic_fairness.qmd
+      - chapters/chapter16/predsets_valid_inttune.qmd
     - chapters/references.qmd
   appendices:
       - chapters/appendices/solutions.qmd # online only

book/chapters/chapter2/data_and_basic_modeling.qmd

@@ -397,6 +397,7 @@ lrn_rpart$param_set
 ```
 
 The output above is a `r ref("ParamSet", aside = TRUE)` object, supplied by the `r ref_pkg("paradox")` package.
+A more detailed introduction of the `paradox` package is provided in @sec-paradox.
 These objects provide information on hyperparameters including their name (`id`), data type (`class`), technically valid ranges for hyperparameter values (`lower`, `upper`), the number of levels possible if the data type is categorical (`nlevels`), the default value from the underlying package (`default`), and finally the set value (`value`).
 The second column references classes defined in `r ref_pkg("paradox")` that determine the class of the parameter and the possible values it can take.
 @tbl-parameters-classes lists the possible hyperparameter types, all of which inherit from `r ref("Domain")`.

book/chapters/chapter4/hyperparameter_optimization.qmd

@@ -72,7 +72,7 @@ These will usually be 'technical' (or 'control') parameters that *provide inform
 
 For numeric hyperparameters (we will explore others later) one must specify the bounds to tune over.
 We do this by constructing a learner and using `r ref("to_tune()")` to set the lower and upper limits for the parameters we want to tune.
-This function allows us to *mark* the hyperparameter as requiring tuning in the specified range.
+This function allows us to *mark* the hyperparameter as requiring tuning in the specified range. Further information on the `r ref("to_tune()")`-function can be found in @sec-paradox-creation-tuning-paramset-from-learner.
 
 ```{r hyperparameter_optimization-003}
 learner = lrn("classif.svm",
@@ -699,6 +699,8 @@ This function takes named arguments of class `r ref("Domain")`, which can be cre
 
 : `r ref("Domain")` Constructors and their resulting `r ref("Domain")`. {#tbl-paradox-define}
 
+More information on advanced hyperparameter specifications using the `paradox`-package will be given in @sec-paradox.
+
 As a simple example, let us look at how to create a search space to tune `cost` and `gamma` again:
 
 ```{r hyperparameter_optimization-037}