Multi-Receiver Online Bayesian Persuasion

Bayesian persuasion studies how an informed sender should partially disclose information to influence the behavior of a self-interested receiver. Classical models make the stringent assumption that the sender knows the receiver’s utility. This can be relaxed by considering an online learning framework in which the sender repeatedly faces a receiver of an unknown, adversarially selected type. We study, for the first time, an online Bayesian persuasion setting with multiple receivers. We focus on the case with no externalities and binary actions, as customary in offline models. Our goal is to design no-regret algorithms for the sender with polynomial per-iteration running time. First, we prove a negative result: for any 0 < α ≤ 1, there is no polynomial-time no-α-regret algorithm when the sender’s utility function is supermodular or anonymous. Then, we focus on the case of submodular sender’s utility functions and we show that, in this case, it is possible to design a polynomial-time no( 1− 1e ) regret algorithm. To do so, we introduce a general online gradient descent scheme to handle online learning problems with a finite number of possible loss functions. This requires the existence of an approximate projection oracle. We show that, in our setting, there exists one such projection oracle which can be implemented in polynomial time.

[1]  Ran Raz,et al.  A parallel repetition theorem , 1995, STOC '95.

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

[3]  Wei Hu,et al.  Online Improper Learning with an Approximation Oracle , 2018, NeurIPS.

[4]  Haifeng Xu,et al.  Regret-Minimizing Bayesian Persuasion , 2021, EC.

[5]  Haifeng Xu.  On the Tractability of Public Persuasion with No Externalities , 2020, SODA.

[6]  Carsten Lund,et al.  Proof verification and hardness of approximation problems , 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

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

[8]  Alexander Schrijver,et al.  Combinatorial optimization. Polyhedra and efficiency. , 2003 .

[9]  Nicola Gatti,et al.  Persuading Voters: It's Easy to Whisper, It's Hard to Speak Loud , 2020, AAAI.

[10]  Martin Grötschel,et al.  The ellipsoid method and its consequences in combinatorial optimization , 1981, Comb..

[11]  D. Mccloskey,et al.  One Quarter of GDP Is Persuasion , 1995 .

[12]  Haifeng Xu,et al.  Targeting and Signaling in Ad Auctions , 2017, SODA.

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

[14]  Dan Garber,et al.  Efficient Online Linear Optimization with Approximation Algorithms , 2017, NIPS.

[15]  Tim Roughgarden,et al.  Minimizing Regret with Multiple Reserves , 2016, EC.

[16]  Gerry Antioch.  Persuasion is now 30 per cent of US GDP , 2013 .

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

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

[19]  Vincent Conitzer,et al.  Signaling in Bayesian Stackelberg Games , 2016, AAMAS.

[20]  Jan Vondrák,et al.  Optimal Approximation for Submodular and Supermodular Optimization with Bounded Curvature , 2017, Math. Oper. Res..

[21]  Jan Vondrák,et al.  Optimal approximation for submodular and supermodular optimization with bounded curvature , 2013, SODA.

[22]  Nicola Gatti,et al.  Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry , 2020, AAAI.

[23]  Yakov Babichenko,et al.  Computational Aspects of Private Bayesian Persuasion , 2016, ArXiv.

[24]  Adam Tauman Kalai,et al.  Playing games with approximation algorithms , 2007, STOC '07.

[25]  Haifeng Xu,et al.  Algorithmic Persuasion with No Externalities , 2017, EC.

[26]  Avinatan Hassidim,et al.  Implementing the Wisdom of Waze , 2015, IJCAI.

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

[28]  Yakov Babichenko,et al.  Algorithmic Aspects of Private Bayesian Persuasion , 2017, ITCS.

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

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

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

[32]  Haifeng Xu,et al.  Algorithmic Bayesian persuasion , 2015, STOC.

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

[34]  Michael J. Todd,et al.  Polynomial Algorithms for Linear Programming , 1988 .

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