Db2une: Tuning Under Pressure via Deep Learning
Summary: Db2une automatically tunes Db2 knobs by encoding queries with QBERT (transformer-based embeddings) and driving a stability-oriented on-policy deep reinforcement learning agent to balance performance and resource use. Multi-phase, metadata-driven training leverages cost estimates and interpolation to avoid executing queries, enabling scalable tuning of large workloads and outperforming expert and state-of-the-art recommenders. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Alexander Bianchi (IBM; York University)
- 2. Andrew Chai (IBM; York University)
- 3. Vincent Corvinelli (IBM)
- 4. Parke Godfrey (IBM; York University)
- 5. Jarek Szlichta (IBM; York University)
- 6. Calisto Zuzarte (IBM)
BibTeX Citation
@article{bianchi_vldb24,
title = {{Db2une: Tuning Under Pressure via Deep Learning}},
author = {Bianchi, Alexander and Chai, Andrew and Corvinelli, Vincent and Godfrey, Parke and Szlichta, Jarek and Zuzarte, Calisto},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {3855--3868},
doi = {10.14778/3685800.3685811},
url = {https://doi.org/10.14778/3685800.3685811},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,222 | SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation | 2026 | VLDB | 5.2056825e-05 |
| 10,290 | 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 | 5.0431863e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 17 of 17 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next