The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence
We infer local influence relations between networked entities from data on outcomes and assess the value of temporal data by formulating relevant binary hypothesis testing problems and characterizing the speed of learning of the correct hypothesis via the Kullback-Leibler divergence, under three dif...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/110806 https://orcid.org/0000-0002-1470-2148 https://orcid.org/0000-0003-2658-8239 |
| _version_ | 1826199220319682560 |
|---|---|
| author | Zoumpoulis, Spyros I. Dahleh, Munther A Tsitsiklis, John N |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Zoumpoulis, Spyros I. Dahleh, Munther A Tsitsiklis, John N |
| author_sort | Zoumpoulis, Spyros I. |
| collection | MIT |
| description | We infer local influence relations between networked entities from data on outcomes and assess the value of temporal data by formulating relevant binary hypothesis testing problems and characterizing the speed of learning of the correct hypothesis via the Kullback-Leibler divergence, under three different types of available data: knowing the set of entities who take a particular action; knowing the order that the entities take an action; and knowing the times of the actions. |
| first_indexed | 2024-09-23T11:16:20Z |
| format | Article |
| id | mit-1721.1/110806 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:16:20Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1108062022-10-01T02:31:22Z The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence Zoumpoulis, Spyros I. Dahleh, Munther A Tsitsiklis, John N Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Institute for Data, Systems, and Society Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Dahleh, Munther A Tsitsiklis, John N We infer local influence relations between networked entities from data on outcomes and assess the value of temporal data by formulating relevant binary hypothesis testing problems and characterizing the speed of learning of the correct hypothesis via the Kullback-Leibler divergence, under three different types of available data: knowing the set of entities who take a particular action; knowing the order that the entities take an action; and knowing the times of the actions. United States. Air Force. Office of Scientific Research (Contract FA9550-09-1-0420). 2017-07-21T18:35:17Z 2017-07-21T18:35:17Z 2016-02 2015-12 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-7886-1 http://hdl.handle.net/1721.1/110806 Dahleh, Munther A., John N. Tsitsiklis, and Spyros I. Zoumpoulis. “The Value of Temporal Data for Learning of Influence Networks: A Characterization via Kullback-Leibler Divergence.” 2015 IEEE 54th Annual Conference on Decision and Control (CDC), Osaka, Japan, 15-18 December, 2015. IEEE, 2015. 2907–2912. https://orcid.org/0000-0002-1470-2148 https://orcid.org/0000-0003-2658-8239 en_US http://dx.doi.org/10.1109/CDC.2015.7402658 2015 54th IEEE Conference on Decision and Control (CDC) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT Web Domain |
| spellingShingle | Zoumpoulis, Spyros I. Dahleh, Munther A Tsitsiklis, John N The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title | The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title_full | The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title_fullStr | The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title_full_unstemmed | The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title_short | The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence |
| title_sort | value of temporal data for learning of influence networks a characterization via kullback leibler divergence |
| url | http://hdl.handle.net/1721.1/110806 https://orcid.org/0000-0002-1470-2148 https://orcid.org/0000-0003-2658-8239 |
| work_keys_str_mv | AT zoumpoulisspyrosi thevalueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence AT dahlehmunthera thevalueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence AT tsitsiklisjohnn thevalueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence AT zoumpoulisspyrosi valueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence AT dahlehmunthera valueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence AT tsitsiklisjohnn valueoftemporaldataforlearningofinfluencenetworksacharacterizationviakullbackleiblerdivergence |