Abstract
How should we evaluate a rumor? We address this question in a setting where multiple agents seek an estimate of the probability, b, of some future binary event. A common uniform prior on b is assumed. A rumor about b meanders through the network, evolving over time. The rumor evolves, not because of ill will or noise, but because agents incorporate private signals about b before passing on the (modified) rumor. The loss to an agent is the (realized) square error of her opinion.
Our setting introduces strategic behavior based on evidence regarding an exogenous event to current models of rumor/influence propagation in social networks.
We study a simple Exponential Moving Average (EMA) for combining experience evidence and trusted advice (rumor), quantifying its resulting performance and comparing it to the optimal achievable using Bayes posterior having access to the agents private signals.
We study the quality of \(p_T\), the prediction of the last agent along a chain of T rumor-mongering agents. The prediction \(p_T\) can be viewed as an aggregate estimator of b that depends on the private signals of T agents. We show that
-
When agents know their position in the rumor-mongering sequence, the expected mean square error of the aggregate estimator is \(\varTheta (\frac{1}{T})\). Moreover, with probability \(1-\delta \), the aggregate estimator’s deviation from b is \(\varTheta \left( \sqrt{\frac{\ln (1/\delta )}{T}}\right) \).
-
If the position information is not available, and agents act strategically, the aggregate estimator has a mean square error of \(O(\frac{1}{\sqrt{T}})\). Furthermore, with probability \(1~-~\delta \), the aggregate estimator’s deviation from b is \(\widetilde{O}\left( \sqrt{\frac{\ln (1/\delta )}{\sqrt{T}}}\right) \).
“Rumor is not always wrong” De vita et moribus Iulii Agricolae — Publius Cornelius TACITUS (56 - 117)
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In a somewhat non-standard use of the Aumann’s model, because there are aspects of the state of the world that are not interesting in and of themselves, whereas in our setting agents are only interested in the underlying probability of the event occurring.
- 2.
Note that \(\widehat{\theta }(\emptyset ) = \frac{1}{2}\) which is consistent with \(B \sim U[0,1]\).
- 3.
References
Abernethy, J., Frongillo,R.M.: A collaborative mechanism for crowdsourcing prediction problems (2011). CoRR, abs/1111.2664
Aumann, R.J.: Agreeing to disagree. Ann. Stat. 4(6), 1236–1239 (1976)
Bala, V., Goyal, S.: Learning from neighbours. Rev. Econ. Stud. 65(3), 595–621 (1998)
Banerjee, A., Fudenberg, D.: Word-of-mouth learning. Games Econ. Behav. 46(1), 1–22 (2004)
Banerjee, A., Guo, X., Wang, H.: On the optimality of conditional expectation as a Bregman predictor. IEEE Trans. Inf. Theory 51(7), 2664–2669 (2005)
David, E., Jon, K.: Networks, Crowds, and Markets: Reasoning About a Highly Connected World. Cambridge University Press, New York (2010)
Ellison, G., Fudenberg, D.: Word-of-mouth communication and social learning. Q. J. Econ. 110(1), 93–125 (1995)
Geanakoplos, J., Polemarchakis, H.M.: We can’t disagree forever. Cowles Foundation Discussion Papers 639, Cowles Foundation for Research in Economics, Yale University, July 1982
McKelvey, R.D., Page, T.: Common knowledge, consensus, and aggregate information. Econometrica 54(1), 109–127 (1986)
Ostrovsky, M.: Information aggregation in dynamic markets with strategic traders. Research Papers 2053, Stanford University, Graduate School of Business, March 2009
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fiat, A., Mansour, Y., Schain, M. (2016). History-Independent Distributed Multi-agent Learning. In: Gairing, M., Savani, R. (eds) Algorithmic Game Theory. SAGT 2016. Lecture Notes in Computer Science(), vol 9928. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-53354-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-662-53354-3_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-53353-6
Online ISBN: 978-3-662-53354-3
eBook Packages: Computer ScienceComputer Science (R0)