Closed mynameisvinn closed 6 years ago
We can discuss this further in https://github.com/dask/dask-ml/issues/161
FYI, https://github.com/dask/dask-ml/pull/221 is implementing Hyperband. This may be a good model for out to structure the code implementing something like http://papers.nips.cc/paper/4522-practical-bayesian-optimization-of-machine-learning-algorithms.pdf
should we consider incorporating bayesian optimization for hyperparameter search?
it could be distributed with across different machines, just as with gridsearch, but would converge much faster.
here is the 2017 nips paper (http://papers.nips.cc/paper/4522-practical-bayesian-optimization-of-machine-learning-algorithms.pdf)