Non-bayesian social learning with uncertain models
© 1991-2012 IEEE. Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a network. Agents iteratively form and communicate beliefs about an unknown state of the world with their neighbors using a learning rule. Existing appr...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2023
|
| Online Access: | https://hdl.handle.net/1721.1/148602 |
| _version_ | 1826200670157406208 |
|---|---|
| author | Hare, JZ Uribe, CA Kaplan, L Jadbabaie, A |
| author2 | Massachusetts Institute of Technology. Institute for Data, Systems, and Society |
| author_facet | Massachusetts Institute of Technology. Institute for Data, Systems, and Society Hare, JZ Uribe, CA Kaplan, L Jadbabaie, A |
| author_sort | Hare, JZ |
| collection | MIT |
| description | © 1991-2012 IEEE. Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a network. Agents iteratively form and communicate beliefs about an unknown state of the world with their neighbors using a learning rule. Existing approaches assume agents have access to precise statistical models (in the form of likelihoods) for the state of the world. However, in many situations, such models must be learned from finite data. We propose a social learning rule that takes into account uncertainty in the statistical models using second-order probabilities. Therefore, beliefs derived from uncertain models are sensitive to the amount of past evidence collected for each hypothesis. These beliefs characterize whether or not the hypotheses are consistent with the true state of the world. We explicitly show the dependency of the generated beliefs with respect to the amount of prior evidence. Furthermore, as the amount of prior evidence goes to infinity, learning occurs and is consistent with traditional social learning theory. |
| first_indexed | 2024-09-23T11:40:02Z |
| format | Article |
| id | mit-1721.1/148602 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:40:02Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1486022023-03-18T03:30:16Z Non-bayesian social learning with uncertain models Hare, JZ Uribe, CA Kaplan, L Jadbabaie, A Massachusetts Institute of Technology. Institute for Data, Systems, and Society Massachusetts Institute of Technology. Department of Civil and Environmental Engineering © 1991-2012 IEEE. Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a network. Agents iteratively form and communicate beliefs about an unknown state of the world with their neighbors using a learning rule. Existing approaches assume agents have access to precise statistical models (in the form of likelihoods) for the state of the world. However, in many situations, such models must be learned from finite data. We propose a social learning rule that takes into account uncertainty in the statistical models using second-order probabilities. Therefore, beliefs derived from uncertain models are sensitive to the amount of past evidence collected for each hypothesis. These beliefs characterize whether or not the hypotheses are consistent with the true state of the world. We explicitly show the dependency of the generated beliefs with respect to the amount of prior evidence. Furthermore, as the amount of prior evidence goes to infinity, learning occurs and is consistent with traditional social learning theory. 2023-03-17T16:49:31Z 2023-03-17T16:49:31Z 2020-01-01 2023-03-17T16:38:13Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/148602 Hare, JZ, Uribe, CA, Kaplan, L and Jadbabaie, A. 2020. "Non-bayesian social learning with uncertain models." IEEE Transactions on Signal Processing, 68. en 10.1109/TSP.2020.3006755 IEEE Transactions on Signal Processing 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 | Hare, JZ Uribe, CA Kaplan, L Jadbabaie, A Non-bayesian social learning with uncertain models |
| title | Non-bayesian social learning with uncertain models |
| title_full | Non-bayesian social learning with uncertain models |
| title_fullStr | Non-bayesian social learning with uncertain models |
| title_full_unstemmed | Non-bayesian social learning with uncertain models |
| title_short | Non-bayesian social learning with uncertain models |
| title_sort | non bayesian social learning with uncertain models |
| url | https://hdl.handle.net/1721.1/148602 |
| work_keys_str_mv | AT harejz nonbayesiansociallearningwithuncertainmodels AT uribeca nonbayesiansociallearningwithuncertainmodels AT kaplanl nonbayesiansociallearningwithuncertainmodels AT jadbabaiea nonbayesiansociallearningwithuncertainmodels |