English

Distributed Estimation of Dynamic Parameters : Regret Analysis

Optimization and Control 2016-03-03 v1 Machine Learning Social and Information Networks

Abstract

This paper addresses the estimation of a time- varying parameter in a network. A group of agents sequentially receive noisy signals about the parameter (or moving target), which does not follow any particular dynamics. The parameter is not observable to an individual agent, but it is globally identifiable for the whole network. Viewing the problem with an online optimization lens, we aim to provide the finite-time or non-asymptotic analysis of the problem. To this end, we use a notion of dynamic regret which suits the online, non-stationary nature of the problem. In our setting, dynamic regret can be recognized as a finite-time counterpart of stability in the mean- square sense. We develop a distributed, online algorithm for tracking the moving target. Defining the path-length as the consecutive differences between target locations, we express an upper bound on regret in terms of the path-length of the target and network errors. We further show the consistency of the result with static setting and noiseless observations.

Keywords

Cite

@article{arxiv.1603.00576,
  title  = {Distributed Estimation of Dynamic Parameters : Regret Analysis},
  author = {Shahin Shahrampour and Alexander Rakhlin and Ali Jadbabaie},
  journal= {arXiv preprint arXiv:1603.00576},
  year   = {2016}
}

Comments

6 pages, To appear in American Control Conference 2016

R2 v1 2026-06-22T13:01:43.038Z