Logarithmic regret bound over diffusion based distributed estimation
Date
2014
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of the 39th International Conference on Acoustics, Speech and Signal Processing, IEEE 2014
Print ISSN
1520-6149
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
8287 - 8291
Language
English
Type
Journal Title
Journal ISSN
Volume Title
Series
Abstract
We provide a logarithmic upper-bound on the regret function of the diffusion implementation for the distributed estimation. For certain learning rates, the bound shows guaranteed performance convergence of the distributed least mean square (DLMS) algorithms to the performance of the best estimation generated with hindsight of spatial and temporal data. We use a new cost definition for distributed estimation based on the widely-used statistical performance measures and the corresponding global regret function. Then, for certain learning rates, we provide an upper-bound on the global regret function without any statistical assumptions.