Bayesian Optimization for Hyperparameter Tuning - Arimo

Bayesian Optimization helped us find a hyperparameter configuration that is better than the one found by Random Search for a neural network on the San Francisco Crimes dataset. People who are familiar with Machine Learning might want to fast forward to Section 3 for details. The code to reproduce the experiments can be found here. Hyperparameter tuning may be one of the most tricky, yet interesting, topics in Machine Learning. For most Machine Learning practitioners, mastering the art of tuning hyperparameters requires not only a solid background in Machine Learning algorithms, but also extensive experience working with real-world datasets.