English

Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms

Machine Learning 2020-10-23 v1 Data Structures and Algorithms

Abstract

We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust, meaning that the algorithm performs well when predictions are accurate and maintains worst-case guarantees. Such algorithms have been studied in a recent line of works due to Lykouris and Vassilvitskii (ICML '18) and Purohit et al (NeurIPS '18). They provide robustness-consistency trade-offs for a variety of online problems. However, they leave open the question of whether these trade-offs are tight, i.e., to what extent to such trade-offs are necessary. In this paper, we provide the first set of non-trivial lower bounds for competitive analysis using machine-learned predictions. We focus on the classic problems of ski-rental and non-clairvoyant scheduling and provide optimal trade-offs in various settings.

Keywords

Cite

@article{arxiv.2010.11443,
  title  = {Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms},
  author = {Alexander Wei and Fred Zhang},
  journal= {arXiv preprint arXiv:2010.11443},
  year   = {2020}
}

Comments

To appear at NeurIPS 2020

R2 v1 2026-06-23T19:32:33.374Z