Skip to yearly menu bar Skip to main content


Spotlight
in
Workshop: Machine Learning for Systems

The Unreasonable Effectiveness of LLMs for Query Optimization (Peter Akioyamen, UPenn)

Peter Akioyamen · Zixuan Yi · Ryan Marcus

[ ] [ Project Page ]
Sun 15 Dec 2:30 p.m. PST — 2:40 p.m. PST
 
presentation: Machine Learning for Systems
Sun 15 Dec 8:15 a.m. PST — 4:30 p.m. PST

Abstract:

Recent work in database query optimization has used complex machine learning strategies, such as customized reinforcement learning schemes. Surprisingly, we show that LLM embeddings of query text contain useful semantic information for query optimization. Specifically, we show that a simple binary classifier deciding between alternative query plans, trained only on a small number of labeled embedded query vectors, can outperform existing heuristic systems. Although we only present some preliminary results, an LLM-powered query optimizer could provide significant benefits, both in terms of performance and simplicity.

Chat is not available.