Learned Index: A Comprehensive Experimental Evaluation
Summary: Comprehensive empirical evaluation and taxonomy of learned indexes, dissecting design choices for position inference/refinement, inserts, concurrency, and bulk-loading within a unified testbed. Benchmarks state-of-the-art learned indexes under identical settings and gives actionable guidance for selection and design. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zhaoyan Sun (Tsinghua University)
- 2. Xuanhe Zhou (Tsinghua University)
- 3. Guoliang Li (Tsinghua University)
BibTeX Citation
@article{sun_vldb23,
title = {{Learned Index: A Comprehensive Experimental Evaluation}},
author = {Sun, Zhaoyan and Zhou, Xuanhe and Li, Guoliang},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {8},
pages = {1992--2004},
doi = {10.14778/3594512.3594528},
url = {https://doi.org/10.14778/3594512.3594528},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 22 of 22 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 31 of 31 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 | 9,599 | Understanding Robustness Issues of Updatable Learned Indexes: [Experiments & Analysis] | 2026 | SIGMOD |
| 2 | 7,368 | Accelerating String-key Learned Index Structures via Memoization-based Incremental Training | 2024 | VLDB |
| 3 | 5,423 | Updatable Learned Indexes Meet Disk-Resident DBMS - From Evaluations to Design Choices | 2023 | SIGMOD |
| 4 | 4,643 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |
| 5 | 6,687 | Making In-Memory Learned Indexes Efficient on Disk | 2024 | SIGMOD |
| 6 | 43 | The Case for Learned Index Structures | 2018 | SIGMOD |
| 7 | 1,551 | Updatable Learned Index with Precise Positions | 2021 | VLDB |
| 8 | 8,214 | Tuning Hierarchical Learned Indexes on Disk and Beyond | 2022 | SIGMOD |
| 9 | 2,806 | Are Updatable Learned Indexes Ready? | 2022 | VLDB |
| 10 | 847 | Benchmarking Learned Indexes | 2021 | VLDB |