Bayesian Learning Without Recall
We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents’ beliefs are formed. They do so by making rational inferences about their obse...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
| Online Access: | http://hdl.handle.net/1721.1/117848 |
| _version_ | 1826214583697670144 |
|---|---|
| author | Jadbabaie, Ali Rahimian, Mohammad Amin Jadbabaie-Moghadam, Ali |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Jadbabaie, Ali Rahimian, Mohammad Amin Jadbabaie-Moghadam, Ali |
| author_sort | Jadbabaie, Ali |
| collection | MIT |
| description | We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents’ beliefs are formed. They do so by making rational inferences about their observations which include a sequence of independent and identically distributed private signals as well as the actions of their neighboring agents at each time. Successive applications of Bayes rule to the entire history of past observations lead to forebodingly complex inferences: due to lack of knowledge about the global network structure, and unavailability of private observations, as well as third party interactions preceding every decision. Such difficulties make Bayesian updating of beliefs an implausible mechanism for social learning. To address these complexities, we consider a Bayesian without Recall model of inference. On the one hand, this model provides a tractable framework for analyzing the behavior of rational agents in social networks. On the other hand, this model also provides a behavioral foundation for the variety of non-Bayesian update rules in the literature. We present the implications of various choices for the structure of the action space and utility functions for such agents and investigate the properties of learning, convergence, and consensus in special cases. |
| first_indexed | 2024-09-23T16:07:47Z |
| format | Article |
| id | mit-1721.1/117848 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T16:07:47Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1178482022-09-29T18:26:44Z Bayesian Learning Without Recall Jadbabaie, Ali Rahimian, Mohammad Amin Jadbabaie-Moghadam, Ali Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Massachusetts Institute of Technology. Institute for Data, Systems, and Society Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Rahimian, Mohammad Amin Jadbabaie-Moghadam, Ali We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents’ beliefs are formed. They do so by making rational inferences about their observations which include a sequence of independent and identically distributed private signals as well as the actions of their neighboring agents at each time. Successive applications of Bayes rule to the entire history of past observations lead to forebodingly complex inferences: due to lack of knowledge about the global network structure, and unavailability of private observations, as well as third party interactions preceding every decision. Such difficulties make Bayesian updating of beliefs an implausible mechanism for social learning. To address these complexities, we consider a Bayesian without Recall model of inference. On the one hand, this model provides a tractable framework for analyzing the behavior of rational agents in social networks. On the other hand, this model also provides a behavioral foundation for the variety of non-Bayesian update rules in the literature. We present the implications of various choices for the structure of the action space and utility functions for such agents and investigate the properties of learning, convergence, and consensus in special cases. United States. Army Research Office. Multidisciplinary University Research Initiative (W911NF-12-1-0509) 2018-09-17T14:55:33Z 2018-09-17T14:55:33Z 2016-11 2018-08-16T17:14:24Z Article http://purl.org/eprint/type/JournalArticle 2373-776X 2373-7778 http://hdl.handle.net/1721.1/117848 Rahimian, M. Amin, and Ali Jadbabaie. “Bayesian Learning Without Recall.” IEEE Transactions on Signal and Information Processing over Networks 3, no. 3 (September 2017): 592–606. http://dx.doi.org/10.1109/TSIPN.2016.2631943 IEEE Transactions on Signal and Information Processing over Networks Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Jadbabaie, Ali Rahimian, Mohammad Amin Jadbabaie-Moghadam, Ali Bayesian Learning Without Recall |
| title | Bayesian Learning Without Recall |
| title_full | Bayesian Learning Without Recall |
| title_fullStr | Bayesian Learning Without Recall |
| title_full_unstemmed | Bayesian Learning Without Recall |
| title_short | Bayesian Learning Without Recall |
| title_sort | bayesian learning without recall |
| url | http://hdl.handle.net/1721.1/117848 |
| work_keys_str_mv | AT jadbabaieali bayesianlearningwithoutrecall AT rahimianmohammadamin bayesianlearningwithoutrecall AT jadbabaiemoghadamali bayesianlearningwithoutrecall |