A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Summary: Statistically-aware end-to-end optimizer for ML inference that cascades feature computation via a cost-model to select high-value, low-cost features. Demonstrates up to 5x speedups with negligible accuracy loss; interactive Jupyter notebooks illustrate applicable workloads and usage. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Peter Kraft (Stanford University)
- 2. Daniel Kang (Stanford University)
- 3. Deepak Narayanan (Stanford University)
- 4. Shoumik Palkar (Stanford University)
- 5. Peter Bailis (Stanford University)
- 6. Matei Zaharia (Stanford University)
BibTeX Citation
@article{kraft_vldb20,
title = {{A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference}},
author = {Kraft, Peter and Kang, Daniel and Narayanan, Deepak and Palkar, Shoumik and Bailis, Peter and Zaharia, Matei},
journal = {PVLDB},
series = {{VLDB} '20},
volume = {13},
number = {12},
pages = {2833--2836},
doi = {10.14778/3415478.3415487},
url = {https://doi.org/10.14778/3415478.3415487},
year = {2020}
}Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,182 | Extending Relational Query Processing with ML Inference | 2020 | CIDR | 8.8982998e-05 |
| 2,662 | End-to-end Optimization of Machine Learning Prediction Queries | 2022 | SIGMOD | 8.1596229e-05 |
| 5,553 | Sommelier: Curating DNN Models for the Masses | 2022 | SIGMOD | 6.0858703e-05 |
| 7,978 | Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines | 2024 | VLDB | 5.4136835e-05 |
| 8,480 | Deep Learning: Systems and Responsibility | 2021 | SIGMOD | 5.333141e-05 |
| 10,123 | RALF: Accuracy-Aware Scheduling for Feature Store Maintenance | 2024 | VLDB | 5.0760214e-05 |
| 11,069 | KEN: An Execution Engine for Unstructured Database Systems | 2026 | VLDB | 4.9793485e-05 |
| 11,786 | Sniffer: A Novel Model Type Detection System against Machine-Learning-as-a-Service Platforms | 2023 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,249 | Evaluating End-to-End Optimization for Data Analytics Applications in Weld | 2018 | VLDB | 8.7549752e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,008 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 2 | 13,691 | Harmonizing ML and Databases: A Symphony of Data (VLDB 2024 Keynote) | 2024 | VLDB |
| 3 | 11,161 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 4 | 3,524 | MLog: Towards Declarative In-Database Machine Learning | 2017 | VLDB |
| 5 | 10,986 | Demonstrating Samsara: A Super-Optimizer for Multimodal Stream Processing | 2026 | VLDB |
| 6 | 13,625 | Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines | 2025 | SIGMOD |
| 7 | 10,044 | Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models | 2022 | VLDB |
| 8 | 281 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD |
| 9 | 7,316 | Interactive Demonstration of Probabilistic Predicates | 2018 | SIGMOD |
| 10 | 11,148 | Demo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations | 2025 | SIGMOD |