@inproceedings{b287f20cbfc742f38a7311e7d50e4e0f,
title = "ROI Maximization in Stochastic Online Decision-Making",
abstract = "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 Π at a rate of order min \{1/(N ∆2), N−1/3\}, where N is the number of innovations and ∆ is the suboptimality gap in Π. 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.",
author = "Nicol{\`o} Cesa-Bianchi and Tommaso Cesari and Yishay Mansour and Vianney Perchet",
note = "Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",
year = "2021",
language = "الإنجليزيّة",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
pages = "9152--9166",
editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, \{Percy S.\} and \{Wortman Vaughan\}, Jenn",
booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",
address = "الولايات المتّحدة",
}