Distributed hyper parameter optimization for dask.

Right now, integration between dask and various single node machine learning libraries are implemented as standalone dask extensions like dask-ml and dask-optuna. These can be used with xgboost when xgboost is performing single node training. That's using `XGBRegressor` and friends with them, instead of using `xgboost.dask.DaskXGBRegressor`. If users want to train the entire dataset on 1 model, the dask interface is required. The underlying issue is xgboost by itself is a distributed learning library employing a MPI like communication framework, but those extensions are designed to extend single node libraries. To resolve it, we need to design python wrappers that can glue them together.

Optuna is an exception as it's using callback function in xgboost, so the xgboost.dask interface can be adopted to optuna. I will submit some changes with demos later. Others like grid searching are more difficult to implement.

Related: https://github.com/dmlc/xgboost/issues/5347

cc @pseudotensor @sandys