Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adversarial Query Synthesis via Bayesian Optimization

Jeffrey Tao, Yimeng Zeng, Haydn Thomas Jones, Natalie Maus, Osbert Bastani, Jacob R. Gardner, Ryan Marcus

TL;DR

This work proposes a Bayesian optimization technique to automatically search for difficult benchmark queries, significantly reducing the amount of manual effort usually required.

Abstract

Benchmark workloads are extremely important to the database management research community, especially as more machine learning components are integrated into database systems. Here, we propose a Bayesian optimization technique to automatically search for difficult benchmark queries, significantly reducing the amount of manual effort usually required. In preliminary experiments, we show that our approach can generate queries with more than double the optimization headroom compared to existing benchmarks.

Adversarial Query Synthesis via Bayesian Optimization

TL;DR

This work proposes a Bayesian optimization technique to automatically search for difficult benchmark queries, significantly reducing the amount of manual effort usually required.

Abstract

Benchmark workloads are extremely important to the database management research community, especially as more machine learning components are integrated into database systems. Here, we propose a Bayesian optimization technique to automatically search for difficult benchmark queries, significantly reducing the amount of manual effort usually required. In preliminary experiments, we show that our approach can generate queries with more than double the optimization headroom compared to existing benchmarks.
Paper Structure (8 sections, 1 equation, 2 figures)

This paper contains 8 sections, 1 equation, 2 figures.

Table of Contents

  1. Introduction
  2. Methods
  3. Plan representation and VAE.
  4. Query VAE.
  5. A Simple SQL Subset
  6. Grammar-constrained decoding for SQL.
  7. Preliminary results
  8. Conclusion and Future Work

Figures (2)

  • Figure 1: CDFs of absolute and relative differences between baseline system (DuckDB) and witness plan for our generated benchmark. Median values at red cross.
  • Figure 2: Comparison of geometric mean relative headroom for four benchmarks. Values for JOB and JOB-Complex are from job_complex. Values for Stack are approximated from bao. Values for "Ours" are computed with respect to the witness plan.