POMACS · 2026
Prediction-Specific Design of Learning-Augmented Algorithms
Proceedings of the ACM on Measurement and Analysis of Computing Systems
Can an algorithm be optimal for the particular prediction it receives?
Strong optimality refines the usual consistency and robustness tradeoff to account for each prediction. A bilevel optimization framework constructs algorithms for ski rental and one max search, with case studies in power management and trading.
Research themes
Open questions
Prediction quality as a decision resource
Which prediction errors actually matter for the decision being made?
Explore open directionsCite this paper
Sizhe Li, Nicolas Christianson, Tongxin Li. Prediction-Specific Design of Learning-Augmented Algorithms. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2026. https://doi.org/10.1145/3788100
BibTeX
@article{tongxin-prediction-specific,
title = {{Prediction-Specific Design of Learning-Augmented Algorithms}},
author = {Sizhe Li and Nicolas Christianson and Tongxin Li},
year = {2026},
journal = {Proceedings of the ACM on Measurement and Analysis of Computing Systems},
url = {https://doi.org/10.1145/3788100},
doi = {10.1145/3788100}
}
Other versions
Related papers
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners
A measure of advice quality connects simulators and payoff predictions to strategic performance. The paper establishes benefits of reliable advice for approximate Stackelberg play and limitations on simultaneously exploiting accurate advice and protecting against inaccurate advice.
PEARL: A Physics-Enhanced Adaptive Residual Learning Framework for PV Modeling
PEARL separates a physical photovoltaic simulator from a learned residual correction. A controlled benchmark compares several machine learning architectures and a coupled modeling baseline, examining accuracy while retaining the physical model as an interpretable reference.
VigilMPC: Certified Online Tube Model Predictive Control for Safe Real-Time Neuromodulation
VigilMPC accepts a predictor update only when a backup plan remains feasible under tightened constraints. Recursive feasibility and constraint satisfaction follow under the tube MPC assumptions. Evaluation uses simulated neural dynamics and a switching benchmark, rather than clinical deployment.