BASE: Bridging the Gap between Cost and Latency for Query Optimization
Summary: BASE: two-stage RL optimizer—train policy on cheap cost signals then transfer a calibrated reward function via an inverse-RL variant to align the policy to latency without costly online execution. Mutual reward–policy refinement improves latency over cost-only learners, cuts training time ≈30% vs SOTA, and generalizes to boost other learned optimizers. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xu Chen (University of Electronic Science and Technology of China)
- 2. Zhen Wang (Alibaba)
- 3. Shuncheng Liu (University of Electronic Science and Technology of China)
- 4. Yaliang Li (Alibaba)
- 5. Kai Zeng (Alibaba)
- 6. Bolin Ding (Alibaba)
- 7. Jingren Zhou (Alibaba)
- 8. Han Su (University of Electronic Science and Technology of China)
- 9. Kai Zheng (University of Electronic Science and Technology of China)
BibTeX Citation
@article{chen_vldb23,
title = {{BASE: Bridging the Gap between Cost and Latency for Query Optimization}},
author = {Chen, Xu and Wang, Zhen and Liu, Shuncheng and Li, Yaliang and Zeng, Kai and Ding, Bolin and Zhou, Jingren and Su, Han and Zheng, Kai},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {8},
pages = {1958--1966},
doi = {10.14778/3594512.3594525},
url = {https://doi.org/10.14778/3594512.3594525},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,462 | PilotScope: Steering Databases with Machine Learning Drivers | 2024 | VLDB | 5.8717744e-05 |
| 10,108 | An Elephant Under The Microscope: Analyzing The Interaction Of Optimizer Components In PostgreSQL | 2025 | SIGMOD | 5.1347137e-05 |
| 10,672 | Optimizing Block Skipping for High-Dimensional Data with Learned Adaptive Curve | 2025 | SIGMOD | 5.093636e-05 |
| 10,884 | Conformal Prediction for Verifiable Learned Query Optimization | 2025 | VLDB | 5.093636e-05 |
| 11,083 | Graph Transformers for Query Plan Representation: Potentials and Challenges | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 18 | How Good Are Query Optimizers, Really? | 2016 | VLDB | 0.00059284255 |
| 154 | Neo: A Learned Query Optimizer | 2019 | VLDB | 0.00028726181 |
| 378 | Bao: Making Learned Query Optimization Practical | 2021 | SIGMOD | 0.00019638121 |
| 1,241 | Balsa: Learning a Query Optimizer Without Expert Demonstrations | 2022 | SIGMOD | 0.00011521639 |
| 2,313 | Active Learning for ML Enhanced Database Systems | 2020 | SIGMOD | 8.762627e-05 |
| 3,998 | Deploying a Steered Query Optimizer in Production at Microsoft | 2022 | SIGMOD | 6.9676473e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,271 | Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective | 2024 | VLDB |
| 2 | 9,601 | Low Rank Learning for Offline Query Optimization | 2025 | SIGMOD |
| 3 | 6,593 | Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis | 2023 | VLDB |
| 4 | 4,643 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |
| 5 | 465 | An End-to-End Learning-based Cost Estimator | 2020 | VLDB |
| 6 | 2,762 | Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection | 2022 | VLDB |
| 7 | 1,241 | Balsa: Learning a Query Optimizer Without Expert Demonstrations | 2022 | SIGMOD |
| 8 | 8,163 | Learned Offline Query Planning via Bayesian Optimization | 2025 | SIGMOD |
| 9 | 5,169 | LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning | 2022 | SIGMOD |
| 10 | 3,051 | Towards a Hands-Free Query Optimizer through Deep Learning | 2019 | CIDR |