Learning to Persuade on the Fly: Robustness Against Ignorance

References

• Agrawal S, Devanur NR (2014) Bandits with concave rewards and convex knapsacks. Proc. Fifteenth ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 989–1006.Google Scholar
• Amani S, Alizadeh M, Thrampoulidis C (2019) Linear stochastic bandits under safety constraints. Adv. Neural Inform. Processing Systems 32:9256–9266.Google Scholar
• Antelmi A, Malandrino D, Scarano V (2019) Characterizing the behavioral evolution of Twitter users and the truth behind the 90-9-1 rule. Companion Proc. 2019 World Wide Web Conf. (Association for Computing Machinery, New York), 1035–1038.Google Scholar
• Aumann RJ, Maschler M, Stearns RE (1995) Repeated Games with Incomplete Information (MIT Press, Cambridge, MA).Google Scholar
• Balcan MF, Blum A, Haghtalab N, Procaccia AD (2015) Commitment without regrets: Online learning in Stackelberg security games. Proc. Sixteenth ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 61–78.Google Scholar
• Bergemann D, Morris S (2016) Bayes correlated equilibrium and the comparison of information structures in games. Theor. Econom. 11(2):487–522.Crossref, Google Scholar
• Bergemann D, Morris S (2019) Information design: A unified perspective. J. Econom. Lit. 57(1):44–95.Crossref, Google Scholar
• Besson L, Kaufmann E (2018) What doubling tricks can and can’t do for multi-armed bandits. Preprint, submitted March 19, https://arxiv.org/abs/1803.06971.Google Scholar
• Camara MK, Hartline JD, Johnsen A (2020) Mechanisms for a no-regret agent: Beyond the common prior. 2020 IEEE 61st Annual Sympos. Foundations of Computer Science FOCS, volume 1 (IEEE, Piscataway, NJ), 259–270.Google Scholar
• Candogan O (2020) Information design in operations. Pushing the Boundaries: Frontiers in Impactful OR/OM Research, INFORMS TutORials in Operations Research (INFORMS, Catonsville, MD), 176–201.Link, Google Scholar
• Cao X, Liu KR (2018) Online convex optimization with time-varying constraints and bandit feedback. IEEE Trans. Automatic Control 64(7):2665–2680.Crossref, Google Scholar
• Cao X, Zhang J, Poor HV (2019) On the time-varying distributions of online stochastic optimization. 2019 Amer. Control Conf. ACC (IEEE, Piscataway, NJ), 1494–1500.Google Scholar
• Castiglioni M, Celli A, Marchesi A, Gatti N (2020) Online Bayesian persuasion. Adv. Neural Inform. Processing Systems 33:16188–16198.Google Scholar
• Chawla S, Hartline JD, Malec D, Sivan B (2013) Prior-independent mechanisms for scheduling. Proc. Forty Fifth Annu. ACM Sympos. Theory Comput. (Association for Computing Machinery, New York), 51–60.Google Scholar
• Chen Y, Liu Y, Podimata C (2020) Learning strategy-aware linear classifiers. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Advances in Neural Information Processing Systems, vol. 33 (Curran Associates, Inc., Red Hook, NY), 15265–15276.Google Scholar
• Dhangwatnotai P, Roughgarden T, Yan Q (2015) Revenue maximization with a single sample. Games Econom. Behav. 91:318–333.Crossref, Google Scholar
• Dong J, Roth A, Schutzman Z, Waggoner B, Wu ZS (2018) Strategic classification from revealed preferences. Proc. 2018 ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 55–70.Google Scholar
• Dughmi S (2017) Algorithmic information structure design: A survey. ACM SIGecom Exchanges 15(2):2–24.Crossref, Google Scholar
• Dughmi S, Xu H (2017) Algorithmic persuasion with no externalities. Proc. 2017 ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 351–368.Google Scholar
• Dughmi S, Xu H (2021) Algorithmic Bayesian persuasion. SIAM J. Comput. 50(3):STOC16-68–STOC16-97.Crossref, Google Scholar
• Dworczak P, Pavan A (2020) Preparing for the worst but hoping for the best: Robust (Bayesian) persuasion. CEPR Discussion Paper No. DP15017, Centre for Economic Policy Research, London.Google Scholar
• Elliott M, Galeotti A, Koh A, Li W (2022) Matching and information design in marketplaces. Preprint, submitted December 13, https://dx.doi.org/10.2139/ssrn.4283968.Google Scholar
• Foucart S, Rauhut H (2013) A Mathematical Introduction to Compressive Sensing (Birkhäuser, New York).Crossref, Google Scholar
• Guo H, Liu X, Wei H, Ying L (2024) Online convex optimization with hard constraints: Toward the best of two worlds and beyond. Proc. 36th Internat. Conf. Adv. Neural Inform. Processing Systems. (Curran Associates Inc., Red Hook, NY), 36426–36439.Google Scholar
• Gur Y, Macnamara G, Morgenstern I, Saban D (2023) Information disclosure and promotion policy design for platforms. Management Sci. 69(10):5883–5903.Link, Google Scholar
• Hahn N, Hoefer M, Smorodinsky R (2020) Prophet inequalities for Bayesian persuasion. Bessiere C, ed. Proc. Twenty-Ninth Internat. Joint Conf. Artificial Intelligence (IJCAI-20) (International Joint Conferences on Artificial Intelligence Organization), 175–181.Google Scholar
• Hahn N, Hoefer M, Smorodinsky R (2022) The secretary recommendation problem. Games Econom. Behav. 134:199–228.Google Scholar
• Haldane JBS (1948) The precision of observed values of small frequencies. Biometrika 35(3/4):297–300.Crossref, Google Scholar
• Hu J, Weng X (2021) Robust persuasion of a privately informed receiver. Econom. Theory 72:909–953.Crossref, Google Scholar
• Jaynes ET (2003) Probability Theory: The Logic of Science (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Kamenica E, Gentzkow M (2011) Bayesian persuasion. Amer. Econom. Rev. 101(6):2590–2615.Crossref, Google Scholar
• Khezeli K, Bitar E (2019) Safe linear stochastic bandits. Preprint, submitted November 21, https://arxiv.org/abs/1911.09501.Google Scholar
• Kim Y, Lee D (2023) Online convex optimization with stochastic constraints: Zero constraint violation and bandit feedback. Preprint, submitted January 26, https://arxiv.org/abs/2301.11267.Google Scholar
• Kleinberg R, Leighton T (2003) The value of knowing a demand curve: Bounds on regret for online posted-price auctions. Proc. 44th Annu. IEEE Sympos. Foundations Comput. Sci. FOCS’03 (IEEE Computer Society, Piscataway, NJ), 594–605.Google Scholar
• Kosterina S (2022) Persuasion with unknown beliefs. Theoret. Econom. 17:1075–1107.Google Scholar
• Kremer I, Mansour Y, Perry M (2014) Implementing the “wisdom of the crowd”. J. Polit. Econom. 122(5):988–1012.Crossref, Google Scholar
• Lattimore T, Szepesvári C (2020) Bandit Algorithms (Cambridge University Press, Cambridge, UK).Crossref, Google Scholar
• Liakopoulos N, Destounis A, Paschos G, Spyropoulos T, Mertikopoulos P (2019) Cautious regret minimization: Online optimization with long-term budget constraints. Kamalika C, Ruslan S, eds. Internat. Conf. Machine Learn., vol. 97 (PMLR, New York), 3944–3952.Google Scholar
• Mahdavi M, Jin R, Yang T (2011) Trading regret for efficiency: Online convex optimization with long term constraints. Preprint, submitted November 25, https://arxiv.org/abs/1111.6082.Google Scholar
• Mahdavi M, Yang T, Jin R (2013) Stochastic convex optimization with multiple objectives. Burges CJ, Bottou L, Welling M, Ghahramani Z, Weinberger KQ, eds. Advances in Neural Information Processing Systems, vol. 26 (Curran Associates, Inc., Red Hook, NY).Google Scholar
• Mansour Y, Slivkins A, Syrgkanis V (2015) Bayesian incentive-compatible bandit exploration. Proc. Sixteenth ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 565–582.Google Scholar
• Mansour Y, Slivkins A, Syrgkanis V, Wu ZS (2016) Bayesian exploration: Incentivizing exploration in Bayesian games. Proc. 2016 ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 661.Google Scholar
• Moradipari A, Thrampoulidis C, Alizadeh M (2020) Stage-wise conservative linear bandits. Adv. Neural Inform. Processing Systems 33:11191–11201.Google Scholar
• Moradipari A, Amani S, Alizadeh M, Thrampoulidis C (2021) Safe linear Thompson sampling with side information. IEEE Trans. Signal Process. 69:3755–3767.Crossref, Google Scholar
• Neely MJ, Yu H (2017) Online convex optimization with time-varying constraints. Preprint, submitted February 15, https://arxiv.org/abs/1702.04783.Google Scholar
• Pacchiano A, Ghavamzadeh M, Bartlett P, Jiang H (2021) Stochastic bandits with linear constraints. Arindam B, Kenji F, eds. Internat. Conf. Artificial Intelligence Statist., vol. 30 (PMLR, New York), 2827–2835.Google Scholar
• Romanyuk G, Smolin A (2019) Cream skimming and information design in matching markets. Amer. Econom. J. Microeconom. 11(2):250–276.Crossref, Google Scholar
• Usmanova I, Krause A, Kamgarpour M (2019) Safe convex learning under uncertain constraints. Kamalika C, Masashi S, eds. 22nd Internat. Conf. Artificial Intelligence Statist., vol. 89 (PMLR, New York), 2106–2114.Google Scholar
• van Mierlo T (2014) The 1% rule in four digital health social networks: An observational study. J. Med. Internet Res. 16(2):e2966.Crossref, Google Scholar
• Villegas C (1977) On the representation of ignorance. J. Amer. Statist. Assoc. 72(359):651–654.Crossref, Google Scholar
• Yang P, Iyer K, Frazier P (2019) Information design in spatial resource competition. Preprint, submitted September 29, https://arxiv.org/abs/1909.12723.Google Scholar
• Yi X, Li X, Yang T, Xie L, Chai T, Johansson K (2021) Regret and cumulative constraint violation analysis for online convex optimization with long term constraints. Marina M, Tong Z, eds. Internat. Conf. Machine Learn., vol. 139 (PMLR, New York), 11998–12008.Google Scholar
• Yi X, Li X, Yang T, Xie L, Chai T, Johansson KH (2023) Regret and cumulative constraint violation analysis for distributed online constrained convex optimization. IEEE Trans. Automatic Control 68(5):2875–2890.Crossref, Google Scholar
• Yu H, Neely MJ, Wei X (2017) Online convex optimization with stochastic constraints. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds. Adv. Neural Inform. Processing Systems, vol. 30 (Curran Associates, Inc., Red Hook, NY).Google Scholar
• Yuan J, Lamperski AG (2018) Online convex optimization for cumulative constraints. Preprint, submitted February 19, https://arxiv.org/abs/1802.06472.Google Scholar