Low Rank Learning for Offline Query Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Zixuan, Tian, Yao, Ives, Zachary G., Marcus, Ryan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909572079288320
author Yi, Zixuan
Tian, Yao
Ives, Zachary G.
Marcus, Ryan
author_facet Yi, Zixuan
Tian, Yao
Ives, Zachary G.
Marcus, Ryan
contents Recent deployments of learned query optimizers use expensive neural networks and ad-hoc search policies. To address these issues, we introduce \textsc{LimeQO}, a framework for offline query optimization leveraging low-rank learning to efficiently explore alternative query plans with minimal resource usage. By modeling the workload as a partially observed, low-rank matrix, we predict unobserved query plan latencies using purely linear methods, significantly reducing computational overhead compared to neural networks. We formalize offline exploration as an active learning problem, and present simple heuristics that reduces a 3-hour workload to 1.5 hours after just 1.5 hours of exploration. Additionally, we propose a transductive Tree Convolutional Neural Network (TCNN) that, despite higher computational costs, achieves the same workload reduction with only 0.5 hours of exploration. Unlike previous approaches that place expensive neural networks directly in the query processing ``hot'' path, our approach offers a low-overhead solution and a no-regressions guarantee, all without making assumptions about the underlying DBMS. The code is available in \href{https://github.com/zixy17/LimeQO}{https://github.com/zixy17/LimeQO}.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low Rank Learning for Offline Query Optimization
Yi, Zixuan
Tian, Yao
Ives, Zachary G.
Marcus, Ryan
Databases
Machine Learning
Recent deployments of learned query optimizers use expensive neural networks and ad-hoc search policies. To address these issues, we introduce \textsc{LimeQO}, a framework for offline query optimization leveraging low-rank learning to efficiently explore alternative query plans with minimal resource usage. By modeling the workload as a partially observed, low-rank matrix, we predict unobserved query plan latencies using purely linear methods, significantly reducing computational overhead compared to neural networks. We formalize offline exploration as an active learning problem, and present simple heuristics that reduces a 3-hour workload to 1.5 hours after just 1.5 hours of exploration. Additionally, we propose a transductive Tree Convolutional Neural Network (TCNN) that, despite higher computational costs, achieves the same workload reduction with only 0.5 hours of exploration. Unlike previous approaches that place expensive neural networks directly in the query processing ``hot'' path, our approach offers a low-overhead solution and a no-regressions guarantee, all without making assumptions about the underlying DBMS. The code is available in \href{https://github.com/zixy17/LimeQO}{https://github.com/zixy17/LimeQO}.
title Low Rank Learning for Offline Query Optimization
topic Databases
Machine Learning
url https://arxiv.org/abs/2504.06399