Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis

Summary: Compare SOTA RL-based learned optimizers to two simple adaptive methods (on-the-fly NLJ/Hash switching and Lookahead Information Passing) implemented in PostgreSQL. Adaptive methods match or often beat RL, need no training, are interpretable, and handle complex queries RL can't. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 13325
Venue: VLDB
Year: 2023
Pagerank: 5.8297039e-05
Overall Rank: 6,593 | 54.77%
DOI: 10.14778/3611479.3611501

Incoming Non-self Citations Over Time

Authors

1. Yunjia Zhang (University of Wisconsin)
2. Yannis Chronis (University of Wisconsin)
3. Jignesh M. Patel (Carnegie Mellon University)
4. Theodoros Rekatsinas (ETH Zurich)

BibTeX Citation

@article{zhang_vldb23,
        title = {{Simple Adaptive Query Processing vs. Learned Query Optimizers: Observations and Analysis}},
        author = {Zhang, Yunjia and Chronis, Yannis and Patel, Jignesh M. and Rekatsinas, Theodoros},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {11},
        pages = {2962--2975},
        doi = {10.14778/3611479.3611501},
        url = {https://doi.org/10.14778/3611479.3611501},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 7 of 7 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,271	Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective	2024	VLDB	5.9326197e-05
8,074	Parachute: Single-Pass Bi-Directional Information Passing	2025	VLDB	5.4929961e-05
9,920	Still Asking: How Good Are Query Optimizers, Really?	2025	VLDB	5.1955087e-05
10,108	An Elephant Under The Microscope: Analyzing The Interaction Of Optimizer Components In PostgreSQL	2025	SIGMOD	5.1347137e-05
10,529	Robust Predicate Transfer with Dynamic Execution	2026	VLDB	5.093636e-05
10,559	OBELISK: Efficient Offline Query Planning with Bayesian Optimization-Informed Language Model Reasoning	2026	VLDB	5.093636e-05
10,881	Robust Plan Evaluation based on Approximate Probabilistic Machine Learning	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 26 of 26 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0024089429
18	How Good Are Query Optimizers, Really?	2016	VLDB	0.00059284255
53	Eddies: Continuously Adaptive Query Processing	2000	SIGMOD	0.00041071971
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035838391
151	Efficient Mid-Query Re-Optimization of Sub-Optimal Query Execution Plans	1998	SIGMOD	0.00029161879
154	Neo: A Learned Query Optimizer	2019	VLDB	0.00028726181
222	Adaptive Selectivity Estimation Using Query Feedback	1994	SIGMOD	0.00024193708
289	Optimization of Dynamic Query Evaluation Plans	1994	SIGMOD	0.00022278876
323	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021264788
378	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00019638121
396	R* Optimizer Validation and Performance Evaluation for Local Queries	1986	SIGMOD	0.00019287574
448	Self-tuning Histograms: Building Histograms Without Looking at Data	1999	SIGMOD	0.00018292618
465	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.0001803934
474	Dynamic Query Evaluation Plans	1989	SIGMOD	0.00017894953
697	Selectivity Estimation for Range Predicates using Lightweight Models	2019	VLDB	0.00014888851
813	Adaptive Ordering of Pipelined Stream Filters	2004	SIGMOD	0.00013846487
1,241	Balsa: Learning a Query Optimizer Without Expert Demonstrations	2022	SIGMOD	0.00011521639
1,815	SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning	2018	VLDB	9.6894541e-05
2,156	Quickstep: A Data Platform Based on the Scaling-Up Approach	2018	VLDB	9.0635624e-05
3,003	Configuration-Parametric Query Optimization for Physical Design Tuning	2008	SIGMOD	7.8620915e-05
3,137	Pushing Data-Induced Predicates Through Joins in Big-Data Clusters	2020	VLDB	7.7204167e-05
3,545	Astrid: Accurate Selectivity Estimation for String Predicates using Deep Learning	2021	VLDB	7.3249967e-05
3,571	Looking Ahead Makes Query Plans Robust: Making the Initial Case with In-Memory Star Schema Data Warehouse Workloads	2017	VLDB	7.2991953e-05
4,283	Lifting the Burden of History from Adaptive Query Processing	2004	VLDB	6.7836167e-05
4,849	Bitvector-aware Query Optimization for Decision Support Queries	2020	SIGMOD	6.4803828e-05
5,284	SQLite: Past, Present, and Future	2022	VLDB	6.2827906e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	9,123	BASE: Bridging the Gap between Cost and Latency for Query Optimization	2023	VLDB
2	3,988	Adaptive Query Processing in the Looking Glass	2005	CIDR
3	3,051	Towards a Hands-Free Query Optimizer through Deep Learning	2019	CIDR
4	9,756	Efficient Query Re-optimization with Judicious Subquery Selections	2023	SIGMOD
5	10,316	GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hints	2026	SIGMOD
6	8,163	Learned Offline Query Planning via Bayesian Optimization	2025	SIGMOD
7	7,978	ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Join Algorithms via Reinforcement Learning	2023	VLDB
8	11,497	Demonstrating ADOPT: Adaptively Optimizing Attribute Orders for Worst-Case Optimal Joins via Reinforcement Learning	2023	VLDB
9	7,809	Can Large Language Models Be Query Optimizer for Relational Databases?	2026	SIGMOD
10	6,271	Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective	2024	VLDB