Back to papers
Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines
Summary: Biathlon, an ML-serving system, exploits model resilience to input perturbations by selecting per-aggregation-feature approximation levels to maximize latency reduction while guaranteeing bounded end-to-end accuracy loss. Evaluated on real pipelines, it achieves 5.3x–16.6x speedups with negligible accuracy drop.
(summarized by gpt-5-mini on Feb 09 2026)
- Paper ID
- 13487
- Venue
- VLDB
- Year
- 2024
- Pagerank
- 4.5903427e-05
- Overall Rank
- 8,057 | 44.01%
- DOI
-
10.14778/3675034.3675052
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 27 of 27 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 14 |
Online Aggregation |
1997 |
SIGMOD |
0.0010813443 |
| 317 |
NoScope: Optimizing Neural Network Queries over Video at Scale |
2017 |
VLDB |
0.0002798145 |
| 606 |
DeepDB: Learn from Data, not from Queries! |
2020 |
VLDB |
0.00019251186 |
| 941 |
Wander Join: Online Aggregation via Random Walks |
2016 |
SIGMOD |
0.00015147831 |
| 1,161 |
VerdictDB: Universalizing Approximate Query Processing |
2018 |
SIGMOD |
0.00013579831 |
| 1,320 |
Quickr: Lazily Approximating Complex AdHoc Queries in BigData Clusters |
2016 |
SIGMOD |
0.00012606067 |
| 1,867 |
Knowing When You’re Wrong: Building Fast and Reliable Approximate Query Processing Systems |
2014 |
SIGMOD |
0.00010264932 |
| 2,354 |
G-OLA: Generalized On-Line Aggregation for Interactive Analysis on Big Data |
2015 |
SIGMOD |
8.9748896e-05 |
| 2,494 |
DBEst: Revisiting Approximate Query Processing Engines with Machine Learning Models |
2019 |
SIGMOD |
8.6457436e-05 |
| 2,583 |
Sample + Seek: Approximating Aggregates with Distribution Precision Guarantee |
2016 |
SIGMOD |
8.4973431e-05 |
| 2,589 |
Database Learning: Toward a Database that Becomes Smarter Every Time |
2017 |
SIGMOD |
8.4868591e-05 |
| 2,809 |
Extending Relational Query Processing with ML Inference |
2020 |
CIDR |
8.0869552e-05 |
| 2,904 |
Evaluating End-to-End Optimization for Data Analytics Applications in Weld |
2018 |
VLDB |
7.9403097e-05 |
| 3,133 |
Relational Confidence Bounds Are Easy With The Bootstrap* |
2005 |
SIGMOD |
7.4979168e-05 |
| 3,260 |
Query Processing on Tensor Computation Runtimes |
2022 |
VLDB |
7.3091312e-05 |
| 3,333 |
A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference |
2020 |
VLDB |
7.2064333e-05 |
| 3,409 |
End-to-end Optimization of Machine Learning Prediction Queries |
2022 |
SIGMOD |
7.1240791e-05 |
| 3,808 |
Turbo-Charging Estimate Convergence in DBO |
2009 |
VLDB |
6.7416988e-05 |
| 4,686 |
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures |
2023 |
VLDB |
5.9929067e-05 |
| 4,745 |
Rafiki: Machine Learning as an Analytics Service System |
2019 |
VLDB |
5.9466323e-05 |
| 5,486 |
Containerized Execution of UDFs: An Experimental Evaluation |
2022 |
VLDB |
5.481452e-05 |
| 6,242 |
Optimizing In-memory Database Engine for AI-powered On-line Decision Augmentation Using Persistent Memory |
2021 |
VLDB |
5.1351431e-05 |
| 6,325 |
Incremental Computation of Common Windowed Holistic Aggregates |
2016 |
VLDB |
5.1052925e-05 |
| 7,920 |
JoinBoost: Grow Trees Over Normalized Data Using Only SQL |
2023 |
VLDB |
4.6120304e-05 |
| 9,372 |
FEBench: A Benchmark for Real-Time Relational Data Feature Extraction |
2023 |
VLDB |
4.3461481e-05 |
| 9,772 |
Everest: A Top-K Deep Video Analytics System |
2022 |
SIGMOD |
4.2815042e-05 |
| 9,789 |
RALF: Accuracy-Aware Scheduling for Feature Store Maintenance |
2024 |
VLDB |
4.2786659e-05 |
Semantically Similar Papers