We propose a self-driving approach to online index selection that eschews the DBA and query optimiser, and instead learns the benefits of viable structures through strategic exploration and direct performance observation.
Cite: R Malinga Perera, Bastian Oetomo, Benjamin IP Rubinstein, and Renata Borovica-Gajic. DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees. In 2021 IEEE 37th International Conference on Data Engineering (ICDE), pages 600–611. IEEE, 2021.