In this lecture, we will discuss some recent work on using machine learning to optimize database systems, looking in particular at a project from MIT and Google called "SageDB". In addition, we will also cover the topic of learned indexes.

• Tim Kraska, Mohammad Alizadeh, Alex Beutel, Ed H. Chi, Jialin Ding, Ani Kristo, Guillaume Leclerc, Samuel Madden, Hongzi Mao, Vikram Nathan. SageDB: A Learned Database System. [PDF]

• Tim Kraska, Alex Beutel, Ed H Chi, Jeffrey Dean, Neoklis Polyzotis. The case for learned index structures. [PDF]

Optionally, you can read the following paper on steering a query optimizer:

• Ryan Marcus, Parimarjan Negi, Hongzi Mao, Nesime Tatbul, Mohammad Alizadeh, Tim Kraska. Bao: Making Learned Query Optimization Practical. [PDF]

Some questions to consider as you read:

• Does SageDB use machine learning in the way you expect? Why or why not?
• What is the idea of "instance optimization" mean, and where does SageDB apply it?