MAINT DOC Fix CircleCI on master (scikit-learn#14586)

* [doc build] Fix underscore in text

* use n-features and \times instead of *

* [doc build] Another fix

Author: rth

doc/modules/ensemble.rst

@@ -925,17 +925,18 @@ trees. Building a traditional decision tree (as in the other GBDTs
 requires sorting the samples at each node (for
 each feature). Sorting is needed so that the potential gain of a split point
 can be computed efficiently. Splitting a single node has thus a complexity
-of :math:`\mathcal{O}(\text{n_features} * n \log(n))` where :math:`n` is the
-number of samples at the node.
+of :math:`\mathcal{O}(n_\text{features} \times n \log(n))` where :math:`n`
+is the number of samples at the node.
 
 :class:`HistGradientBoostingClassifier` and
 :class:`HistGradientBoostingRegressor`, in contrast, do not require sorting the
 feature values and instead use a data-structure called a histogram, where the
 samples are implicitly ordered. Building a histogram has a
 :math:`\mathcal{O}(n)` complexity, so the node splitting procedure has a
-:math:`\mathcal{O}(\text{n_features} * n)` complexity, much smaller than the
-previous one. In addition, instead of considering :math:`n` split points, we
-here consider only ``max_bins`` split points, which is much smaller.
+:math:`\mathcal{O}(n_\text{features} \times n)` complexity, much smaller
+than the previous one. In addition, instead of considering :math:`n` split
+points, we here consider only ``max_bins`` split points, which is much
+smaller.
 
 In order to build histograms, the input data `X` needs to be binned into
 integer-valued bins. This binning procedure does require sorting the feature