Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms

ICLR 2026 Conference Submission12742 Authors

Keywords: Learning-augmented algorithms, online algorithms, competitive analysis, performance evaluation metrics, decision theory

TL;DR: The paper introduces novel deterministic and stochastic decision-theoretic metrics that guide the development of better learning-augmented online algorithms

Abstract: We initiate the systematic study of decision-theoretic metrics in the design and analysis of algorithms with machine-learned predictions. We introduce approaches based on both deterministic measures such as distance-based evaluation, that help us quantify how close the algorithm is to an ideal solution, and stochastic measures that balance the trade-off between the algorithm's performance and the risk associated with the imperfect oracle. These approaches allow us to quantify the algorithm's performance across the full spectrum of the prediction error, and thus choose the best algorithm within an entire class of otherwise incomparable ones. We apply our framework to three well-known problems from online decision making, namely ski-rental, one-max search, and contract scheduling.

Primary Area: optimization

Submission Number: 12742