Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning
Summary: UDO is a unified offline tuner optimizing txn code variants, indexes, and DB parameters for workloads via reinforcement learning. It differentiates heavy vs light parameters, delays rewards for costly changes, and uses a cost-aware planner to amortize expensive data-structure creation, validated with real queries on Postgres/MySQL (TPC-H/TPC-C). (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Junxiong Wang (Cornell University)
- 2. Immanuel Trummer (Cornell University)
- 3. Debabrota Basu (INRIA)
BibTeX Citation
@inproceedings{wang_sigmod21,
title = {{Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning}},
author = {Wang, Junxiong and Trummer, Immanuel and Basu, Debabrota},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3452754},
url = {https://dl.acm.org/doi/10.1145/3448016.3452754},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,586 | Make Your Database System Dream of Electric Sheep: Towards Self-Driving Operation | 2021 | VLDB | 7.2834069e-05 |
| 3,926 | UDO: Universal Database Optimization using Reinforcement Learning | 2021 | VLDB | 7.0128068e-05 |
| 7,785 | Tastes Great! Less Filling! High Performance and Accurate Training Data Collection for Self-Driving Database Management Systems | 2022 | SIGMOD | 5.5450355e-05 |
| 7,978 | ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Join Algorithms via Reinforcement Learning | 2023 | VLDB | 5.514996e-05 |
| 8,042 | Grep: A Graph Learning Based Database Partitioning System | 2023 | SIGMOD | 5.5015896e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 498 | QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning | 2019 | VLDB | 0.00017440583 |
| 1,481 | Magic mirror in my hand, which is the best in the land? An Experimental Evaluation of Index Selection Algorithms | 2020 | VLDB | 0.00010644613 |
| 2,154 | Leveraging Lock Contention to Improve OLTP Application Performance | 2016 | VLDB | 9.0745745e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,600 | A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning | 2023 | SIGMOD |
| 2 | 11,548 | DeepO: A Learned Query Optimizer | 2022 | SIGMOD |
| 3 | 498 | QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning | 2019 | VLDB |
| 4 | 6,271 | Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective | 2024 | VLDB |
| 5 | 3,003 | Configuration-Parametric Query Optimization for Physical Design Tuning | 2008 | SIGMOD |
| 6 | 5,171 | An Efficient Transfer Learning Based Configuration Adviser for Database Tuning | 2024 | VLDB |
| 7 | 4,273 | User-Defined Operators: Efficiently Integrating Custom Algorithms into Modern Databases | 2022 | VLDB |
| 8 | 2,811 | Constrained Physical Design Tuning | 2008 | VLDB |
| 9 | 334 | An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning | 2019 | SIGMOD |
| 10 | 3,926 | UDO: Universal Database Optimization using Reinforcement Learning | 2021 | VLDB |