diff --git a/doc/gpu/index.rst b/doc/gpu/index.rst
index 5c335e66a..1f8d2d9e2 100644
--- a/doc/gpu/index.rst
+++ b/doc/gpu/index.rst
@@ -46,6 +46,8 @@ Supported parameters
 +--------------------------------+--------------+
 | ``max_bin``                    | |tick|       |
 +--------------------------------+--------------+
+| ``gamma``                      | |tick|       |
++--------------------------------+--------------+
 | ``gpu_id``                     | |tick|       |
 +--------------------------------+--------------+
 | ``n_gpus`` (deprecated)        | |tick|       |
@@ -75,9 +77,13 @@ The GPU algorithms currently work with CLI, Python and R packages. See :doc:`/bu
   :caption: Python example
 
   param['gpu_id'] = 0
-  param['max_bin'] = 16
   param['tree_method'] = 'gpu_hist'
 
+.. code-block:: python
+  :caption: With Scikit-Learn interface
+
+  XGBRegressor(tree_method='gpu_hist', gpu_id=0)
+
 
 Single Node Multi-GPU
 =====================
@@ -85,9 +91,10 @@ Single Node Multi-GPU
 
 Multi-node Multi-GPU Training
 =============================
-XGBoost supports fully distributed GPU training using `Dask
-<https://dask.org/>`_. See Python documentation :ref:`dask_api` and worked examples `here
-<https://github.com/dmlc/xgboost/tree/master/demo/dask>`_.
+XGBoost supports fully distributed GPU training using `Dask <https://dask.org/>`_. For
+getting started see our tutorial :doc:`/tutorials/dask` and worked examples `here
+<https://github.com/dmlc/xgboost/tree/master/demo/dask>`_, also Python documentation
+:ref:`dask_api` for complete reference.
 
 
 Objective functions
diff --git a/python-package/xgboost/sklearn.py b/python-package/xgboost/sklearn.py
index 74d52393e..66efb01fa 100644
--- a/python-package/xgboost/sklearn.py
+++ b/python-package/xgboost/sklearn.py
@@ -101,8 +101,8 @@ class XGBModel(XGBModelBase):
 
         .. note::
 
-           Using gblinear booster with shotgun updater is
-           nondeterministic as it uses Hogwild algorithm.
+           Using gblinear booster with shotgun updater is nondeterministic as
+           it uses Hogwild algorithm.
 
     missing : float, optional
         Value in the data which needs to be present as a missing value. If
@@ -960,8 +960,10 @@ class XGBRanker(XGBModel):
         random_state : int
             Random number seed.
 
-            .. note:: Using gblinear booster with shotgun updater is
-            nondeterministic as it uses Hogwild algorithm.
+        .. note::
+
+           Using gblinear booster with shotgun updater is nondeterministic as
+           it uses Hogwild algorithm.
 
         missing : float, optional
             Value in the data which needs to be present as a missing value. If