PerfGuard: Deploying ML-for-Systems without Performance Regressions, Almost!
Summary: PerfGuard provides a pre-production safeguard for ML-for-systems, reducing deployment regressions. It confines search to query-plan deltas, learns delta-cost signals with a DL pipeline, and highlights key plan components, showing offline promise for relational DBs. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Remmelt Ammerlaan (Microsoft)
- 2. Gilbert Antonius (Microsoft)
- 3. Marc Friedman (Microsoft)
- 4. H M Sajjad Hossain (Microsoft)
- 5. Alekh Jindal (Microsoft)
- 6. Peter Orenberg (Microsoft)
- 7. Hiren Patel (Microsoft)
- 8. Shi Qiao (Microsoft)
- 9. Vijay Ramani (Microsoft)
- 10. Lucas Rosenblatt (Microsoft)
- 11. Abhishek Roy (Microsoft)
- 12. Irene Shaffer (Microsoft)
- 13. Soundarajan Srinivasan (Microsoft)
- 14. Markus Weimer (Microsoft)
BibTeX Citation
@article{ammerlaan_vldb21,
title = {{PerfGuard: Deploying ML-for-Systems without Performance Regressions, Almost!}},
author = {Ammerlaan, Remmelt and Antonius, Gilbert and Friedman, Marc and Hossain, H M Sajjad and Jindal, Alekh and Orenberg, Peter and Patel, Hiren and Qiao, Shi and Ramani, Vijay and Rosenblatt, Lucas and Roy, Abhishek and Shaffer, Irene and Srinivasan, Soundarajan and Weimer, Markus},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {13},
pages = {3362--3375},
doi = {10.14778/3484224.3484233},
url = {https://doi.org/10.14778/3484224.3484233},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 25 of 25 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 | 282 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD |
| 2 | 5,042 | Leveraging Query Logs and Machine Learning for Parametric Query Optimization | 2022 | VLDB |
| 3 | 9,082 | Machine Learning for Graph Data Management and Query Processing | 2025 | VLDB |
| 4 | 6,298 | Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective | 2024 | VLDB |
| 5 | 3,057 | Towards a Hands-Free Query Optimizer through Deep Learning | 2019 | CIDR |
| 6 | 8,969 | Conformal Prediction for Verifiable Learned Query Optimization | 2025 | VLDB |
| 7 | 4,743 | Machine Learning for Databases | 2021 | VLDB |
| 8 | 5,188 | Database Workload Characterization with Query Plan Encoders | 2022 | VLDB |
| 9 | 2,837 | Query Performance Prediction for Concurrent Queries using Graph Embedding | 2020 | VLDB |
| 10 | 560 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |