The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. We propose to learn a pure data-driven model.
Our lab members Nadja Geisler and Benjamin Hättasch talked about about the Deep Learning Hype and its consequences and impacts at the 36C3 in Leipzig
IDEBench: A new Benchmark for Interactive Data Exploration / DB4ML: An In-Memory Database Kernel with Machine Learning Support / DBPal: A Fully Pluggable NL2SQL Training Pipeline
Get your seat now: http://www.fgdb-symposium.de/ for more info!
In this paper, we propose an alternative approach to learn DBMS components.