A Practical Theory of Generalization in Selectivity Learning
Summary: Proves learnability of signed-measure selectivity predictors and provides out-of-distribution generalization bounds beyond the PAC framework. Derives two practical strategies that empirically boost OOD selectivity accuracy and query latency while retaining in-distribution performance. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Peizhi Wu (University of Pennsylvania)
- 2. Haoshu Xu (University of Pennsylvania)
- 3. Ryan Marcus (University of Pennsylvania)
- 4. Zachary G. Ives (University of Pennsylvania)
BibTeX Citation
@article{wu_vldb25,
title = {{A Practical Theory of Generalization in Selectivity Learning}},
author = {Wu, Peizhi and Xu, Haoshu and Marcus, Ryan and Ives, Zachary G.},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {6},
pages = {1811--1824},
doi = {10.14778/3725688.3725708},
url = {https://doi.org/10.14778/3725688.3725708},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,294 | Data-Agnostic Cardinality Learning from Imperfect Workloads | 2025 | VLDB | 5.0431863e-05 |
| 10,802 | BaCon: Efficient Batch Processing of Counting Queries | 2026 | VLDB | 4.9793485e-05 |
| 10,924 | TATA: An Efficient Framework for Task Transfer in Query Plan Representation | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 37 of 37 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,354 | Hashed Samples: Selectivity Estimators For Set Similarity Selection Queries | 2008 | VLDB |
| 2 | 1,542 | Improved Selectivity Estimation by Combining Knowledge from Sampling and Synopses | 2018 | VLDB |
| 3 | 9,333 | Deep Query Optimization | 2019 | SIGMOD |
| 4 | 1,156 | QuickSel: Quick Selectivity Learning with Mixture Models | 2020 | SIGMOD |
| 5 | 5,911 | On Efficient Approximate Queries over Machine Learning Models | 2023 | VLDB |
| 6 | 8,276 | Consistent and Flexible Selectivity Estimation for High-Dimensional Data | 2021 | SIGMOD |
| 7 | 692 | Selectivity Estimation for Range Predicates using Lightweight Models | 2019 | VLDB |
| 8 | 3,210 | Efficiently Approximating Selectivity Functions using Low Overhead Regression Models | 2020 | VLDB |
| 9 | 1,580 | Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries | 2020 | SIGMOD |
| 10 | 7,332 | Selectivity Functions of Range Queries are Learnable* | 2022 | SIGMOD |