The Holon Approach for Simultaneously Tuning Multiple Components in a Self-Driving Database Management System with Machine Learning via Synthesized Proto-Actions
Summary: Proto-X holistically tunes multiple DBMS configuration spaces, learning cross-space similarities and synthesizing proto-actions to coordinate search rather than sequentially tuning knobs, hints, and indexes. On PostgreSQL, it handles orders-of-magnitude larger spaces and improves performance up to 53% over prior methods. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. William Zhang (Carnegie Mellon University)
- 2. Wan Shen Lim (Carnegie Mellon University)
- 3. Matthew Butrovich (Carnegie Mellon University)
- 4. Andrew Pavlo (Carnegie Mellon University)
BibTeX Citation
@article{zhang_vldb24,
title = {{The Holon Approach for Simultaneously Tuning Multiple Components in a Self-Driving Database Management System with Machine Learning via Synthesized Proto-Actions}},
author = {Zhang, William and Lim, Wan Shen and Butrovich, Matthew and Pavlo, Andrew},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {11},
pages = {3373--3387},
doi = {10.14778/3681954.3682007},
url = {https://doi.org/10.14778/3681954.3682007},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,984 | Hit the Gym: Accelerating Query Execution to Efficiently Bootstrap Behavior Models for Self-Driving Database Management Systems | 2024 | VLDB | 5.3395569e-05 |
| 9,601 | Low Rank Learning for Offline Query Optimization | 2025 | SIGMOD | 5.2487799e-05 |
| 9,771 | Rockhopper: A Robust Optimizer for Spark Configuration Tuning in Production Environment | 2025 | SIGMOD | 5.2209769e-05 |
| 10,128 | Survivorship Bias in Industrial Database Workloads | 2026 | CIDR | 5.093636e-05 |
| 10,506 | This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch! | 2026 | SIGMOD | 5.093636e-05 |
| 10,706 | Automated Database Tuning vs. Human-Based Tuning in a Simulated Stressful Work Environment: A Demonstration of the Database Gym | 2025 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 17 of 67 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.