Accelerating Machine Learning Inference with Probabilistic Predicates
Summary: Proposes probabilistic predicates to prune data blobs before expensive UDF feature extraction, with accuracy-aware filtering. Augments a cost-based optimizer to select plans from simple probabilistic predicates, enabling up to 10x ML inference speedups. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yao Lu (Microsoft; University of Washington)
- 2. Aakanksha Chowdhery (Microsoft; Princeton University)
- 3. Srikanth Kandula (Microsoft)
- 4. Surajit Chaudhuri (Microsoft)
BibTeX Citation
@inproceedings{lu_sigmod18,
title = {{Accelerating Machine Learning Inference with Probabilistic Predicates}},
author = {Lu, Yao and Chowdhery, Aakanksha and Kandula, Srikanth and Chaudhuri, Surajit},
series = {{SIGMOD} '18},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3183713.3183751},
url = {https://dl.acm.org/doi/10.1145/3183713.3183751},
year = {2018}
}Incoming Citations (Sorted by Pagerank)
Showing 50 of 60 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 24 | Spark SQL: Relational Data Processing in Spark | 2015 | SIGMOD | 0.00054865648 |
| 30 | SCOPE: Easy and Efficient Parallel Processing of Massive Data Sets | 2008 | VLDB | 0.00051174276 |
| 32 | Hive - A Warehousing Solution Over a Map-Reduce Framework | 2009 | VLDB | 0.00050111008 |
| 132 | Predicate Migration: Optimizing Queries with Expensive Predicates | 1993 | SIGMOD | 0.00030378624 |
| 284 | NoScope: Optimizing Neural Network Queries over Video at Scale | 2017 | VLDB | 0.00022370521 |
| 813 | Adaptive Ordering of Pipelined Stream Filters | 2004 | SIGMOD | 0.00013846487 |
| 1,124 | Query Optimization by Predicate Move-Around | 1994 | VLDB | 0.00012087356 |
| 1,826 | Optimizing Disjunctive Queries with Expensive Predicates | 1994 | SIGMOD | 9.6721003e-05 |
| 3,945 | Exploiting Correlations for Expensive Predicate Evaluation | 2015 | SIGMOD | 7.0055154e-05 |
| 4,435 | Filtering with Approximate Predicates | 1998 | VLDB | 6.7078883e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,845 | Query-Driven Learning for Next Generation Predictive Modeling & Analytics | 2019 | SIGMOD |
| 2 | 5,225 | Approximate Lifted Inference with Probabilistic Databases | 2015 | VLDB |
| 3 | 9,353 | On Efficient Approximate Queries over Machine Learning Models | 2023 | VLDB |
| 4 | 4,481 | Dynamically Optimizing Queries over Large Scale Data Platforms | 2014 | SIGMOD |
| 5 | 3,945 | Exploiting Correlations for Expensive Predicate Evaluation | 2015 | SIGMOD |
| 6 | 11,166 | PLAQUE: Automated Predicate Learning at Query Time | 2024 | SIGMOD |
| 7 | 3,698 | Optimizing MPF Queries: Decision Support and Probabilistic Inference | 2007 | SIGMOD |
| 8 | 7,176 | Interactive Demonstration of Probabilistic Predicates | 2018 | SIGMOD |
| 9 | 9,882 | Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models | 2022 | VLDB |
| 10 | 4,114 | Optimizing Machine Learning Inference Queries with Correlative Proxy Models | 2022 | VLDB |