Communication Dans Un Congrès Année : 2025

Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search

Résumé

One-max search is a classic problem in online decision-making, in which a trader acts on a sequence of revealed prices and accepts one of them irrevocably to maximize its profit. The problem has been studied both in probabilistic and in worst-case settings, notably through competitive analysis, and more recently in learning-augmented settings in which the trader has access to a prediction on the sequence. However, existing approaches either lack smoothness, or do not achieve optimal worst-case guarantees: they do not attain the best possible trade-off between the consistency and the robustness of the algorithm. We close this gap by presenting the first algorithm that simultaneously achieves both of these important objectives. Furthermore, we show how to leverage the obtained smoothness to provide an analysis of one-max search in stochastic learning-augmented settings which capture randomness in both the observed prices and the prediction.

Fichier principal
Vignette du fichier
2502.05720v1.pdf (1.74 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05080719 , version 1 (22-05-2025)

Licence

Identifiants

Citer

Ziyad Benomar, Lorenzo Croissant, Vianney Perchet, Spyros Angelopoulos. Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search. ICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. ⟨hal-05080719⟩
459 Consultations
408 Téléchargements

Altmetric

Partager

  • More