Distributed estimation and learning over heterogeneous networks
Name
Distributed Estimation and Learning over.pdf
Size
364.64 KB
Format
Adobe PDF
Checksum (MD5)
f02c9cee69387ab6dea98d85a2fbb9a7
Author(s)
Rahimian, Mohammad Amin
Jadbabaie-Moghadam, Ali
Date Issued
February 2017
Journal
2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Rahimian, M. Amin and Jadbabaie, Ali. “Distributed Estimation and Learning over Heterogeneous Networks.” 2016 54th Annual Allerton Conference on Communication, Control, and Computing, September 2016, Monticello, Illinois, USA, Institute of Electrical and Electronics Engineers (IEEE), February 2017
Version
Author's final manuscript
Abstract
We consider several estimation and learning problems that networked agents face when making decisions given their uncertainty about an unknown variable. Our methods are designed to efficiently deal with heterogeneity in both size and quality of the observed data, as well as heterogeneity over time (intermittence). The goal of the studied aggregation schemes is to efficiently combine the observed data that is spread over time and across several network nodes, accounting for all the network heterogeneities. Moreover, we require no form of coordination beyond the local neighborhood of every network agent or sensor node. The three problems that we consider are (i) maximum likelihood estimation of the unknown given initial data sets, (ii) learning the true model parameter from streams of data that the agents receive intermittently over time, and (iii) minimum variance estimation of a complete sufficient statistic from several data points that the networked agents collect over time. In each case, we rely on an aggregation scheme to combine the observations of all agents; moreover, when the agents receive streams of data over time, we modify the update rules to accommodate the most recent observations. In every case, we demonstrate the efficiency of our algorithms by proving convergence to the globally efficient estimators given the observations of all agents. We supplement these results by investigating the rate of convergence and providing finite-time performance guarantees.
MIT Department
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ALLERTON.2016.7852386
