Regret-Minimizing Bayesian Persuasion

We study a Bayesian persuasion setting with binary actions (adopt and reject) for Receiver. We examine the following question - how well can Sender perform, in terms of persuading Receiver to adopt, when ignorant of Receiver's utility? We take a robust (adversarial) approach to study this problem; that is, our goal is to design signaling schemes for Sender that perform well for all possible Receiver's utilities. We measure performance of signaling schemes via the notion of (additive) regret: the difference between Sender's hypothetically optimal utility had she known Receiver's utility function and her actual utility induced by the given scheme. On the negative side, we show that if Sender has no knowledge at all about Receiver's utility, then Sender has no signaling scheme that performs robustly well. On the positive side, we show that if Sender only knows Receiver's ordinal preferences of the states of nature - i.e., Receiver's utility upon adoption is monotonic as a function of the state - then Sender can guarantee a surprisingly low regret even when the number of states tends to infinity. In fact, we exactly pin down the minimum regret value that Sender can guarantee in this case, which turns out to be at most 1/e. We further show that such positive results are not possible under the alternative performance measure of a multiplicative approximation ratio by proving that no constant ratio can be guaranteed even for monotonic Receiver's utility; this may serve to demonstrate the merits of regret as a robust performance measure that is not too pessimistic. Finally, we analyze an intermediate setting in between the no-knowledge and the ordinal-knowledge settings.

[1]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[2]  Xi Weng,et al.  Robust persuasion of a privately informed receiver , 2018, Economic Theory.

[3]  A. Pavan,et al.  Preparing for the Worst but Hoping for the Best: Robust (Bayesian) Persuasion , 2020, SSRN Electronic Journal.

[4]  D. MacKenzie,et al.  The use of knowledge about society , 2008 .

[5]  Peter Bro Miltersen,et al.  Send mixed signals: earn more, work less , 2012, EC '12.

[6]  M. Sion On general minimax theorems , 1958 .

[7]  Vijay V. Vazirani,et al.  Approximation Algorithms , 2001, Springer Berlin Heidelberg.

[8]  Eran Shmaya,et al.  The Interval Structure of Optimal Disclosure , 2019, Econometrica.

[9]  Haifeng Xu,et al.  Exploring Information Asymmetry in Two-Stage Security Games , 2015, AAAI.

[10]  Emir Kamenica,et al.  Bayesian Persuasion , 2009 .

[11]  Gabriel Carroll,et al.  Robustness in Mechanism Design and Contracting , 2019, Annual Review of Economics.

[12]  Li Han,et al.  Mixture Selection, Mechanism Design, and Signaling , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[13]  J. Schreiber Foundations Of Statistics , 2016 .

[14]  Nick Gravin,et al.  Correlation-Robust Analysis of Single Item Auction , 2019, SODA.

[15]  Ozan Candogan,et al.  Information Design in Operations , 2020, SSRN Electronic Journal.

[16]  Moshe Tennenholtz,et al.  Signaling Schemes for Revenue Maximization , 2012, TEAC.

[17]  David Lingenbrink,et al.  Optimal Signaling Mechanisms in Unobservable Queues , 2018, Oper. Res..

[18]  Tim Roughgarden,et al.  Revenue maximization with a single sample , 2010, EC '10.

[19]  Piotr Dworczak,et al.  The Simple Economics of Optimal Persuasion , 2017, Journal of Political Economy.

[20]  Alberto Marchesi,et al.  Online Bayesian Persuasion , 2020, NeurIPS.

[21]  Shaddin Dughmi,et al.  Algorithmic information structure design: a survey , 2017, SECO.

[22]  Herbert E. Scarf,et al.  A Min-Max Solution of an Inventory Problem , 1957 .

[23]  Laurent Mathevet,et al.  On Information Design in Games , 2020, Journal of Political Economy.

[24]  Dimitris Bertsimas,et al.  Optimal Design for Multi-Item Auctions: A Robust Optimization Approach , 2014, Math. Oper. Res..

[25]  Leonid Hurwicz,et al.  Incentive Structures Maximizing Residual Gain Under Incomplete Information , 1978 .

[26]  Richard Cole,et al.  The sample complexity of revenue maximization , 2014, STOC.

[27]  Gabriel D. Carroll Robustness and Separation in Multidimensional Screening , 2017 .

[28]  Gabriel D. Carroll Robustness and Linear Contracts , 2015 .

[29]  Nick Gravin,et al.  Separation in Correlation-Robust Monopolist Problem with Budget , 2018, SODA.

[30]  Yu Cheng,et al.  Hardness Results for Signaling in Bayesian Zero-Sum and Network Routing Games , 2015, EC.

[31]  Yakov Babichenko,et al.  Private Bayesian Persuasion , 2019, J. Econ. Theory.

[32]  T. Roughgarden,et al.  Beyond the Worst-Case Analysis of Algorithms , 2019 .

[33]  Ricardo Alonso,et al.  Persuading Voters , 2015 .

[34]  Leonard J. Savage,et al.  The Theory of Statistical Decision , 1951 .

[35]  Paul R. Milgrom,et al.  Putting Auction Theory to Work: The Simultaneous Ascending Auction , 1999, Journal of Political Economy.

[36]  Tim Roughgarden,et al.  Simple versus Optimal Contracts , 2018, EC.

[37]  Ozan Candogan,et al.  Persuasion in Networks: Public Signals and k-Cores , 2019, EC.

[38]  Andriy Zapechelnyuk,et al.  Persuasion of a Privately Informed Receiver , 2016 .

[39]  Nicolas Vieille,et al.  Optimal dynamic information provision , 2014, Games Econ. Behav..

[40]  Yishay Mansour,et al.  Bayesian Exploration: Incentivizing Exploration in Bayesian Games , 2016, EC.

[41]  Emir Kamenica,et al.  Bayesian Persuasion and Information Design , 2019, Annual Review of Economics.

[42]  D. Bergemann,et al.  Information Design: A Unified Perspective , 2017, Journal of Economic Literature.

[43]  T. Roughgarden,et al.  Approximately Optimal Mechanism Design , 2018, Annual Review of Economics.

[44]  Haifeng Xu,et al.  Information Disclosure as a Means to Security , 2015, AAMAS.

[45]  Jérôme Renault,et al.  Repeated Games with Incomplete Information , 2009, Encyclopedia of Complexity and Systems Science.

[46]  Abraham Wald,et al.  Statistical Decision Functions , 1951 .