A Caltech Library Service

A Deterministic Protocol for Sequential Asymptotic Learning

Cheng, Yu and Hann-Caruthers, Wade and Tamuz, Omer (2018) A Deterministic Protocol for Sequential Asymptotic Learning. In: 2018 IEEE International Symposium on Information Theory (ISIT). IEEE , Piscataway, NJ, pp. 1735-1738. ISBN 978-1-5386-4780-6.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


In the classic herding model, agents receive private signals about an underlying binary state of nature, and act sequentially to choose one of two possible actions, after observing the actions of their predecessors. We investigate what types of behaviors lead to asymptotic learning, where agents will eventually converge to the right action in probability. It is known that for rational agents and bounded signals, there will not be asymptotic learning. Does it help if the agents can be cooperative rather than act selfishly? This is simple to achieve if the agents are allowed to use randomized protocols. In this paper, we provide the first deterministic protocol under which asymptotic learning occurs. In addition, our protocol has the advantage of being much simpler than previous protocols.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Tamuz, Omer0000-0002-0111-0418
Additional Information:© 2018 IEEE. Part of this work was done while Yu Cheng was a student at the University of Southern California. Yu Cheng was supported in part by Shang-Hua Teng’s Simons Investigator Award. Omer Tamuz was supported in part by grant #419427 from the Simons Foundation.
Funding AgencyGrant Number
Simons Foundation419427
Record Number:CaltechAUTHORS:20181126-153354872
Persistent URL:
Official Citation:Y. Cheng, W. Hann-Caruthers and O. Tamuz, "A Deterministic Protocol for Sequential Asymptotic Learning," 2018 IEEE International Symposium on Information Theory (ISIT), Vail, CO, 2018, pp. 1735-1738. doi: 10.1109/ISIT.2018.8437859
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:91194
Deposited By: Tony Diaz
Deposited On:27 Nov 2018 17:59
Last Modified:16 Nov 2021 03:39

Repository Staff Only: item control page