Back to papers
Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective
Summary: Analyzes ML-centric pitfalls in learned query optimizers—training data generation, arbitrary train/validation splits, and inconsistent benchmarking—and introduces a standardized end-to-end ML evaluation framework for LQOs. Rigorous cross-split experiments show PostgreSQL often outperforms current LQOs, challenging claimed RL-driven gains.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 13398
- Venue
- VLDB
- Year
- 2024
- Pagerank
- 4.8643538e-05
- Overall Rank
- 7,008 | 51.25%
- DOI
-
10.14778/3654621.3654625
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 11 of 11 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 6,685 |
How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks |
2025 |
SIGMOD |
4.9627485e-05 |
| 7,126 |
Debunking the Myth of Join Ordering: Toward Robust SQL Analytics |
2025 |
SIGMOD |
4.8232367e-05 |
| 8,020 |
The Holon Approach for Simultaneously Tuning Multiple Components in a Self-Driving Database Management System with Machine Learning via Synthesized Proto-Actions |
2024 |
VLDB |
4.6040862e-05 |
| 8,488 |
Can Large Language Models Be Query Optimizer for Relational Databases? |
2026 |
SIGMOD |
4.4998609e-05 |
| 8,956 |
T3: Accurate and Fast Performance Prediction for Relational Database Systems With Compiled Decision Trees |
2025 |
SIGMOD |
4.4214154e-05 |
| 9,587 |
Low Rank Learning for Offline Query Optimization |
2025 |
SIGMOD |
4.3215645e-05 |
| 10,018 |
GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hints |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,038 |
Understanding Robustness Issues of Updatable Learned Indexes: [Experiments & Analysis] |
2026 |
SIGMOD |
4.1945683e-05 |
| 10,217 |
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 |
4.1945683e-05 |
| 10,241 |
Robust Predicate Transfer with Dynamic Execution |
2026 |
VLDB |
4.1945683e-05 |
| 10,271 |
OBELISK: Efficient Offline Query Planning with Bayesian Optimization-Informed Language Model Reasoning |
2026 |
VLDB |
4.1945683e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 71 |
How Good Are Query Optimizers, Really? |
2016 |
VLDB |
0.00059038975 |
| 115 |
Eddies: Continuously Adaptive Query Processing |
2000 |
SIGMOD |
0.00046221215 |
| 333 |
Neo: A Learned Query Optimizer |
2019 |
VLDB |
0.00027206884 |
| 608 |
DeepDB: Learn from Data, not from Queries! |
2020 |
VLDB |
0.00019235898 |
| 640 |
Bao: Making Learned Query Optimization Practical |
2021 |
SIGMOD |
0.00018759152 |
| 910 |
NeuroCard: One Cardinality Estimator for All Tables |
2021 |
VLDB |
0.00015423056 |
| 1,638 |
Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation |
2022 |
VLDB |
0.00011049779 |
| 2,121 |
Balsa: Learning a Query Optimizer Without Expert Demonstrations |
2022 |
SIGMOD |
9.5017232e-05 |
| 3,348 |
Lero: A Learning-to-Rank Query Optimizer |
2023 |
VLDB |
7.1904529e-05 |
| 3,658 |
Towards a Hands-Free Query Optimizer through Deep Learning |
2019 |
CIDR |
6.8704209e-05 |
| 3,727 |
Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection |
2022 |
VLDB |
6.8141709e-05 |
| 4,462 |
LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans |
2023 |
VLDB |
6.1611784e-05 |
| 5,334 |
LEON: A New Framework for ML-Aided Query Optimization |
2023 |
VLDB |
5.5649836e-05 |
| 7,011 |
Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis |
2023 |
VLDB |
4.8629458e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 11,318 |
Can Transfer Learning be used to build a Query Optimizer? |
2022 |
CIDR |
4.1945683e-05 |
| 6,667 |
Leveraging Query Logs and Machine Learning for Parametric Query Optimization |
2022 |
VLDB |
4.9688874e-05 |
| 8,659 |
Learned Offline Query Planning via Bayesian Optimization |
2025 |
SIGMOD |
4.4722928e-05 |
| 6,685 |
How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks |
2025 |
SIGMOD |
4.9627485e-05 |
| 3,348 |
Lero: A Learning-to-Rank Query Optimizer |
2023 |
VLDB |
7.1904529e-05 |
| 3,658 |
Towards a Hands-Free Query Optimizer through Deep Learning |
2019 |
CIDR |
6.8704209e-05 |
| 11,350 |
DeepO: A Learned Query Optimizer |
2022 |
SIGMOD |
4.1945683e-05 |
| 10,880 |
RankPQO: Learning-to-Rank for Parametric Query Optimization |
2025 |
VLDB |
4.1945683e-05 |
| 7,011 |
Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis |
2023 |
VLDB |
4.8629458e-05 |
| 8,488 |
Can Large Language Models Be Query Optimizer for Relational Databases? |
2026 |
SIGMOD |
4.4998609e-05 |