Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications

Learning-augmented algorithms combine fallible predictions with formal performance guarantees. This survey reviews prediction interfaces, error measures, consistency–robustness trade-offs, and five construction mechanisms across online optimization, caching, learned data structures, graph problems, and mechanism design. It distinguishes theorem-level upper bounds from matched asymptotic dependence, separates formal guarantees from empirical evidence, and outlines open problems in cost-aware prediction, endogenous error, semantic predictors, and benchmarking.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• benchmarks