ROI Maximization in Stochastic Online Decision-Making - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

ROI Maximization in Stochastic Online Decision-Making

Résumé

We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regularly receive proposals for technological innovations and want to quickly decide whether they are worth implementing. We design an algorithm for learning ROI-maximizing decision-making policies over a sequence of innovation proposals. Our algorithm provably converges to an optimal policy in class $\Pi$ at a rate of order $\min\big\{1/(N\Delta^2), N^{-1/3}\}$, where $N$ is the number of innovations and $\Delta$ is the suboptimality gap in $\Pi$. A significant hurdle of our formulation, which sets it aside from other online learning problems such as bandits, is that running a policy does not provide an unbiased estimate of its performance.
Fichier principal
Vignette du fichier
main.pdf (365.18 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02976864 , version 1 (23-10-2020)
hal-02976864 , version 2 (15-02-2021)
hal-02976864 , version 3 (30-06-2021)
hal-02976864 , version 4 (22-12-2021)

Identifiants

Citer

Nicolò Cesa-Bianchi, Tommaso R Cesari, Yishay Mansour, Vianney Perchet. ROI Maximization in Stochastic Online Decision-Making. 2021. ⟨hal-02976864v4⟩
329 Consultations
229 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More