ROI Maximization in Stochastic Online Decision-Making

Nicolò Cesa-Bianchi; Tommaso Cesari; Yishay Mansour; Vianney Perchet

ROI Maximization in Stochastic Online Decision-Making

Nicolò Cesa-Bianchi, Tommaso Cesari, Yishay Mansour, Vianney Perchet

School of Computer Science

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Pages	9152-9166
Number of pages	15
ISBN (Electronic)	9781713845393
State	Published - 2021
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: 6 Dec 2021 → 14 Dec 2021

Publication series

Name	Advances in Neural Information Processing Systems
Volume	11

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	6/12/21 → 14/12/21

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Cesa-Bianchi, N., Cesari, T., Mansour, Y., & Perchet, V. (2021). ROI Maximization in Stochastic Online Decision-Making. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 9152-9166). (Advances in Neural Information Processing Systems; Vol. 11).

Cesa-Bianchi, Nicolò ; Cesari, Tommaso ; Mansour, Yishay et al. / ROI Maximization in Stochastic Online Decision-Making. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. 2021. pp. 9152-9166 (Advances in Neural Information Processing Systems).

@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",

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",

}

Cesa-Bianchi, N, Cesari, T, Mansour, Y & Perchet, V 2021, ROI Maximization in Stochastic Online Decision-Making. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 11, pp. 9152-9166, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 6/12/21.

ROI Maximization in Stochastic Online Decision-Making. / Cesa-Bianchi, Nicolò; Cesari, Tommaso; Mansour, Yishay et al.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. 2021. p. 9152-9166 (Advances in Neural Information Processing Systems; Vol. 11).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - ROI Maximization in Stochastic Online Decision-Making

AU - Cesa-Bianchi, Nicolò

AU - Cesari, Tommaso

AU - Mansour, Yishay

AU - Perchet, Vianney

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85125029994&partnerID=8YFLogxK

M3 - منشور من مؤتمر

T3 - Advances in Neural Information Processing Systems

SP - 9152

EP - 9166

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

Y2 - 6 December 2021 through 14 December 2021

ER -

Cesa-Bianchi N, Cesari T, Mansour Y, Perchet V. ROI Maximization in Stochastic Online Decision-Making. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. 2021. p. 9152-9166. (Advances in Neural Information Processing Systems).

ROI Maximization in Stochastic Online Decision-Making

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this