- Title
- Convergence analysis for Guassian belief propagation: dynamic behaviour of marginal covariances
- Creator
- Sui, Tianju; Marelli, Damián; Fu, Minyue
- Relation
- 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Proceedings of the 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (Shanghai, China 20-25 March, 2016) p. 2599-2602
- Publisher Link
- http://dx.doi.org/10.1109/ICASSP.2016.7472147
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Resource Type
- conference paper
- Date
- 2016
- Description
- Despite of its wide success in many distributed statistical learning applications, the well-known Gaussian belief propagation (BP) algorithm still lacks sufficient understanding at the theoretical level. This paper studies the convergence of Gaussian BP by analyzing the dynamic behaviour of the marginal covariances. We show, under a mild technical assumption, that the information matrices (i.e., the inverses of marginal covariances) are guaranteed to converge exponentially to positive-definite matrices. The convergence rate is explicitly characterized. This result is a key step to the understanding of the dynamic behaviour of the BP iterations.
- Subject
- belief propagation; Gaussian belief propagation; statistical learning; distributed state estimation
- Identifier
- http://hdl.handle.net/1959.13/1339348
- Identifier
- uon:28234
- Identifier
- ISBN:9781479999880
- Language
- eng
- Reviewed
- Hits: 1066
- Visitors: 1001
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|