@incollection{publications44215,
       booktitle = {Advances in Neural Information Processing Systems (Online)},
           title = {ROI maximization in stochastic online decision-making},
          author = {Nicolo Cesa-Bianchi and Cesari Tommaso and Yishay Mansour and Vianney Perchet},
       publisher = {Neural Information Processing Systems Foundation.},
            year = {2021},
         journal = {Advances in Neural Information Processing Systems 34 (NeurIPS)},
             url = {https://publications.ut-capitole.fr/id/eprint/44215/},
        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 {\ensuremath{\Pi}} 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 {\ensuremath{\Pi}}. A signi?cant 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.}
}