LEO - DB2's LEarning Optimizer

Summary: LEO, DB2's LEarning Optimizer, uses a feedback loop to repair cardinality estimates by comparing forecasts with actuals at each QEP step. Online or offline, incremental or batched, it updates costs and statistics across operators (joins, DISTINCT, GROUP BY) with low overhead and large potential gains. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h4d27b9e0c3a031e3
Venue: VLDB
Year: 2001
Pagerank: 0.00034050614
Overall Rank: 98 | 99.35%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Michael Stillger (Siebel Systems, Inc.)
2. Guy Lohman (IBM)
3. Volker Markl (IBM)
4. Mokhtar Kandil (IBM)

BibTeX Citation

@article{stillger_vldb01,
        title = {{LEO - DB2's LEarning Optimizer}},
        author = {Stillger, Michael and Lohman, Guy and Markl, Volker and Kandil, Mokhtar},
        journal = {PVLDB},
        series = {{VLDB} '01},
        year = {2001}
}

Incoming Citations (Sorted by Pagerank)

Showing 23 of 123 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,550	ROME: Robust Query Optimization via Parallel Multi-Plan Execution	2024	SIGMOD	5.3030089e-05
8,672	FusionInsight LibrA: Huawei’s Enterprise Cloud Data Analytics Platform	2018	VLDB	5.2753524e-05
8,872	SkinnerMT: Parallelizing for Efficiency and Robustness in Adaptive Query Processing on Multicore Platforms	2023	VLDB	5.2459616e-05
8,902	Tiresias: Enabling Predictive Autonomous Storage and Indexing	2022	VLDB	5.2387388e-05
9,583	Athena: An Effective Learning-based Framework for Query Optimizer Performance Improvement	2025	SIGMOD	5.140977e-05
9,587	Engineering High-Performance Database Engines	2014	VLDB	5.1391768e-05
9,662	Low Rank Learning for Offline Query Optimization	2025	SIGMOD	5.1283524e-05
9,753	A Practical Theory of Generalization in Selectivity Learning	2025	VLDB	5.1159926e-05
9,888	Detecting Attribute Dependencies from Query Feedback	2007	VLDB	5.1020175e-05
10,014	Selectivity Estimation for Queries Containing Predicates over Set-Valued Attributes	2023	SIGMOD	5.0838565e-05
10,143	Still Asking: How Good Are Query Optimizers, Really?	2025	VLDB	5.0597449e-05
10,212	Thriving in the No Man’s Land between Compilers and Databases	2019	CIDR	5.0490854e-05
10,249	Turbo-Charging SPJ Query Plans with Learned Physical Join Operator Selections	2022	VLDB	5.0412674e-05
10,257	PRICE: A Pretrained Model for Cross-Database Cardinality Estimation	2025	VLDB	5.039379e-05
10,327	Data-Agnostic Cardinality Learning from Imperfect Workloads	2025	VLDB	5.0241309e-05
11,011	Ultron: History-Based Query Optimization at Databricks	2026	VLDB	4.9605343e-05
11,827	Anser: Adaptive Information Sharing Framework of AnalyticDB	2023	VLDB	4.9605343e-05
12,438	Capturing the Laws of (Data) Nature	2015	CIDR	4.9605343e-05
12,594	DBMS Metrology: Measuring Query Time	2013	SIGMOD	4.9605343e-05
12,826	Visualizing the robustness of query execution	2009	CIDR	4.9605343e-05
13,166	Adaptive Distributed Query Processing	2003	VLDB	4.9605343e-05
13,183	SMART: Making DB2 (More) Autonomic	2002	VLDB	4.9605343e-05
14,213	Automated Statistics Collection in Action	2005	SIGMOD	-

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 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	0.0023948467
37	Improved Histograms for Selectivity Estimation of Range Predicates	1996	SIGMOD	0.00047654188
91	On the Propagation of Errors in the Size of Join Results	1991	SIGMOD	0.00034691614
103	Selectivity Estimation Without the Attribute Value Independence Assumption	1997	VLDB	0.00033847446
149	Efficient Mid-Query Re-Optimization of Sub-Optimal Query Execution Plans	1998	SIGMOD	0.00028910892
234	Adaptive Selectivity Estimation Using Query Feedback	1994	SIGMOD	0.00023726296
242	Fast Incremental Maintenance of Approximate Histograms	1997	VLDB	0.00023327437
426	Cost-based Query Scrambling for Initial Delays	1998	SIGMOD	0.00018432573
457	Self-tuning Histograms: Building Histograms Without Looking at Data	1999	SIGMOD	0.00017915659
960	Selectivity Estimation and Query Optimization in Large Databases with Highly Skewed Distributions of Column Values	1988	VLDB	0.00012825107
3,009	Multiple Join Size Estimation by Virtual Domains (extended abstract)	1993	PODS	7.7439468e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,261	Sampling-Based Query Re-Optimization	2016	SIGMOD
2	5,794	Lemo: A Cache-Enhanced Learned Optimizer for Concurrent Queries	2023	SIGMOD
3	142	Neo: A Learned Query Optimizer	2019	VLDB
4	6,672	Speeding Up End-to-end Query Execution via Learning-based Progressive Cardinality Estimation	2023	SIGMOD
5	11,907	DeepO: A Learned Query Optimizer	2022	SIGMOD
6	4,247	LEON: A New Framework for ML-Aided Query Optimization	2023	VLDB
7	10,769	LIO: A lightweight and interpretable query optimizer based on an evolutionary forest	2026	VLDB
8	10,392	E-LQO: A Comprehensive Energy Evaluation Framework for Learned Query Optimization	2027	SIGMOD
9	2,190	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB
10	8,309	Learning Table Access Cardinalities with LEO	2002	SIGMOD