This repository holds a notebook to explain how Bayesian optimization can be used on a concrete case to fine-tune a database configuration.
A secondary notebook has been added with a more complex use case to visualize how Bayesian optimization may also be used with non-elementary behaviors with noise.
To run the notebooks by yourself, be sure to use a Jupyter kernel with the required packages (see requirements.txt).
- D. Van Aken, A. Pavlo, G. J. Gordon, B. Zhang, Automatic Database Management System Tuning Through Large-scale Machine Learning, 2017 - Paper - Repo : Original idea
- S. Duan, V. Thummala, S. Babu - Tuning Database Configuration Parameters with iTuned, 2009 - Paper : Original idea
- Scikit-Optimize repository : Great package and documentation