BIFOLD Colloquium 2023/03/10
March
10,
2023 
13:00
- 13:45
Why Machine Learning for Automatically Optimizing Databases Doesn't Work
Location: TU Berlin, Main building, Straße des 17. Juni 135, 10623 Berlin, Room: H0107
In case you want to join the Colloquium via Zoom, please contact: pr@bifold.berlin.
Abstract: Database management systems (DBMSs) are complex software that requires sophisticated tuning to work efficiently for a given workload and operating environment. Such tuning requires considerable effort from experienced administrators, which is not scalable for large DBMS fleets. This problem has led to research on using machine learning (ML) to devise strategies to optimize DBMS configurations for any application, including automatic physical database design, knob configuration, and query tuning. Despite the many academic papers that tout the benefits of using ML to optimize databases, there have been only a few major success stories in industry in the last decade.
In this talk, Andy Pavlo discusses the challenges of using ML-enhanced tuning methods to optimize databases. He will address specific assumptions that researchers make about production database environments that are incorrect and identify why ML is not always the best solution to solving real-world database problems. As part of this, he will discuss state-of-the-art academic research and real-world tuning implementations.
Speaker: Andy Pavlo is an Associate Professor with Indefinite Tenure in the Computer Science Department at Carnegie Mellon University. He is also the co-founder of the OtterTune automated database optimization start-up. His research interests focus on database management systems, specifically main memory systems, self-driving / autonomous architectures, transaction processing systems, and large-scale data analytics.