Back to papers
AXE: A Task Decomposition Approach to Learned LSM Tuning
Summary: AXE decomposes LSM tuning into (1) training a learned surrogate cost model from logs or existing performance models and (2) synthesizing many training samples to train a learned tuner that optimizes the surrogate, avoiding costly online executions. Outperforms BO 71% of the time with 100x lower tuning overhead, handles categorical knobs, scales across instances without retraining, and reduces reliance on expert cost models/solvers.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 14205
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.1945683e-05
- Overall Rank
- 10,849 | 24.53%
- DOI
-
10.14778/3773731.3773735
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
Outgoing Citations (Sorted by Pagerank)
Showing 30 of 30 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 158 |
Automated Selection of Materialized Views and Indexes for SQL Databases |
2000 |
VLDB |
0.00040071492 |
| 183 |
Automatic Database Management System Tuning Through Large-scale Machine Learning |
2017 |
SIGMOD |
0.00036721403 |
| 237 |
An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server |
1997 |
VLDB |
0.00031726304 |
| 408 |
Database Cracking |
2007 |
CIDR |
0.00023953844 |
| 514 |
An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning |
2019 |
SIGMOD |
0.0002124895 |
| 609 |
Monkey: Optimal Navigable Key-Value Store |
2017 |
SIGMOD |
0.0001923446 |
| 782 |
QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning |
2019 |
VLDB |
0.00016729063 |
| 806 |
An End-to-End Learning-based Cost Estimator |
2020 |
VLDB |
0.00016434274 |
| 1,311 |
Dostoevsky: Better Space-Time Trade-Offs for LSM-Tree Based Key-Value Stores via Adaptive Removal of Superfluous Merging |
2018 |
SIGMOD |
0.00012657439 |
| 1,438 |
AsterixDB: A Scalable, Open Source BDMS |
2014 |
VLDB |
0.00011973592 |
| 1,610 |
MyRocks: LSM-Tree Database Storage Engine Serving Facebook's Social Graph |
2020 |
VLDB |
0.00011148094 |
| 2,157 |
The Data Calculator*: Data Structure Design and Cost Synthesis from First Principles and Learned Cost Models |
2018 |
SIGMOD |
9.416022e-05 |
| 2,606 |
Design Continuums and the Path Toward Self-Designing Key-Value Stores that Know and Learn |
2019 |
CIDR |
8.4645832e-05 |
| 3,522 |
ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases |
2021 |
SIGMOD |
7.0096727e-05 |
| 3,625 |
Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings |
2020 |
SIGMOD |
6.9055212e-05 |
| 3,812 |
Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation |
2022 |
VLDB |
6.7373184e-05 |
| 4,227 |
Cosine: A Cloud-Cost Optimized Self-Designing Key-Value Storage Engine |
2022 |
VLDB |
6.3434324e-05 |
| 4,380 |
LlamaTune: Sample-Efficient DBMS Configuration Tuning |
2022 |
VLDB |
6.2396606e-05 |
| 4,804 |
Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload |
2021 |
SIGMOD |
5.910467e-05 |
| 4,864 |
COLT: Continuous On-Line Database Tuning |
2006 |
SIGMOD |
5.8689388e-05 |
| 5,258 |
One Model to Rule them All: Towards Zero-Shot Learning for Databases |
2022 |
CIDR |
5.5998705e-05 |
| 6,113 |
Compactionary: A Dictionary for LSM Compactions |
2022 |
SIGMOD |
5.20426e-05 |
| 6,398 |
Endure: A Robust Tuning Paradigm for LSM Trees Under Workload Uncertainty |
2022 |
VLDB |
5.0819209e-05 |
| 6,456 |
From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems |
2019 |
SIGMOD |
5.0564619e-05 |
| 6,520 |
Foundations of Automated Database Tuning |
2006 |
VLDB |
5.0307595e-05 |
| 7,620 |
Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads |
2023 |
SIGMOD |
4.693568e-05 |
| 7,753 |
Rethinking Learned Cost Models: Why Start from Scratch? |
2023 |
SIGMOD |
4.660151e-05 |
| 8,009 |
CAMAL: Optimizing LSM-trees via Active Learning |
2024 |
SIGMOD |
4.6066863e-05 |
| 9,071 |
Structural Designs Meet Optimality: Exploring Optimized LSM-tree Structures in A Colossal Configuration Space |
2024 |
SIGMOD |
4.4025274e-05 |
| 9,190 |
MLOS in Action: Bridging the Gap Between Experimentation and Auto-Tuning in the Cloud |
2024 |
VLDB |
4.3768215e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 8,491 |
SA-LSM: Optimize Data Layout for LSM-tree Based Storage using Survival Analysis |
2022 |
VLDB |
4.4993073e-05 |
| 9,386 |
Rethinking The Compaction Policies in LSM-trees |
2025 |
SIGMOD |
4.3455975e-05 |
| 4,380 |
LlamaTune: Sample-Efficient DBMS Configuration Tuning |
2022 |
VLDB |
6.2396606e-05 |
| 3,564 |
Accordion: Better Memory Organization for LSM Key-Value Stores |
2018 |
VLDB |
6.9669032e-05 |
| 5,791 |
Dissecting, Designing, and Optimizing LSM-based Data Stores |
2022 |
SIGMOD |
5.3268999e-05 |
| 8,009 |
CAMAL: Optimizing LSM-trees via Active Learning |
2024 |
SIGMOD |
4.6066863e-05 |
| 1,366 |
SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data |
2017 |
VLDB |
0.00012357685 |
| 6,398 |
Endure: A Robust Tuning Paradigm for LSM Trees Under Workload Uncertainty |
2022 |
VLDB |
5.0819209e-05 |
| 5,918 |
Breaking Down Memory Walls: Adaptive Memory Management in LSM-based Storage Systems |
2021 |
VLDB |
5.2737135e-05 |
| 7,743 |
Efficient Data Ingestion and Query Processing for LSM-Based Storage Systems |
2019 |
VLDB |
4.6626575e-05 |