Back to papers
A Systematic Study on Early Stopping Metrics in HPO and the Implications of Uncertainty
Summary: Systematic study of early-stopping metric choice in HPO/NAS: using training loss (vs. validation loss) in early stages boosts HPO outcomes up to 24.76%. Introduce uncertainty-aware metrics that add up to ~4% extra gain under budget constraints, improving reliability and resource efficiency for scalable early-stopping.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 13818
- Venue
- VLDB
- Year
- 2025
- Pagerank
- 4.1945683e-05
- Overall Rank
- 10,560 | 26.54%
- DOI
-
10.14778/3725688.3725689
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 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 43 |
Models and Issues in Data Stream Systems |
2002 |
PODS |
0.00072723062 |
| 192 |
HoloClean: Holistic Data Repairs with Probabilistic Inference |
2017 |
VLDB |
0.00035728858 |
| 254 |
Snorkel: Rapid Training Data Creation with Weak Supervision |
2018 |
VLDB |
0.00030540555 |
| 782 |
QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning |
2019 |
VLDB |
0.00016729063 |
| 921 |
Democratizing Data Science through Interactive Curation of ML Pipelines |
2019 |
SIGMOD |
0.00015337438 |
| 2,122 |
SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle |
2020 |
CIDR |
9.4989076e-05 |
| 2,839 |
VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition |
2021 |
VLDB |
8.0378978e-05 |
| 3,522 |
ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases |
2021 |
SIGMOD |
7.0096727e-05 |
| 3,812 |
Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation |
2022 |
VLDB |
6.7373184e-05 |
| 3,869 |
MagicScaler: Uncertainty-aware, Predictive Autoscaling |
2023 |
VLDB |
6.6802432e-05 |
| 4,399 |
HUNTER: An Online Cloud Database Hybrid Tuning System for Personalized Requirements |
2022 |
SIGMOD |
6.2225151e-05 |
| 4,748 |
Rafiki: Machine Learning as an Analytics Service System |
2019 |
VLDB |
5.9526539e-05 |
| 4,842 |
Towards Dynamic and Safe Configuration Tuning for Cloud Databases |
2022 |
SIGMOD |
5.8826802e-05 |
| 9,192 |
Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale |
2022 |
VLDB |
4.3765131e-05 |
| 11,224 |
Homomorphic Compression: Making Text Processing on Compression Unlimited |
2023 |
SIGMOD |
4.1945683e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 6,019 |
Uncertain Centroid based Partitional Clustering of Uncertain Data |
2012 |
VLDB |
5.2415551e-05 |
| 3,727 |
Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection |
2022 |
VLDB |
6.8141709e-05 |
| 3,812 |
Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation |
2022 |
VLDB |
6.7373184e-05 |
| 9,344 |
Hippo: Sharing Computations in Hyper-Parameter Optimization |
2022 |
VLDB |
4.3539442e-05 |
| 13,203 |
High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data |
2022 |
PODS |
- |
| 4,395 |
Scalable Asynchronous Gradient Descent Optimization for Out-of-Core Models |
2017 |
VLDB |
6.2244283e-05 |
| 6,986 |
A Cost-based Optimizer for Gradient Descent Optimization |
2017 |
SIGMOD |
4.8727048e-05 |
| 10,164 |
ESTune: Bayesian Uncertainty-Guided Early Stopping for Database Configuration Tuning |
2026 |
SIGMOD |
4.1945683e-05 |
| 8,433 |
Supporting User-Defined Functions on Uncertain Data |
2013 |
VLDB |
4.514792e-05 |
| 9,192 |
Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale |
2022 |
VLDB |
4.3765131e-05 |