Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks
文献类型：期刊论文
| 作者 | Zhaorong Zhang; Minyue Fu |
| 刊名 | IEEE/CAA Journal of Automatica Sinica
 |
| 出版日期 | 2020 |
| 卷号 | 7期号:3页码:668-673 |
| 关键词 | Belief propagation distributed algorithm distributed estimation Gaussian belief propagation Markov networks |
| ISSN号 | 2329-9266 |
| DOI | 10.1109/JAS.2020.1003105 |
| 英文摘要 | Gaussian belief propagation algorithm (GaBP) is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network in a finite number of iterations when the underlying Gaussian graph is acyclic. It is also known more recently that the algorithm produces correct marginal means asymptotically for cyclic Gaussian graphs under the condition of walk summability (or generalised diagonal dominance). This paper extends this convergence result further by showing that the convergence is exponential under the generalised diagonal dominance condition, and provides a simple bound for the convergence rate. Our results are derived by combining the known walk summability approach for asymptotic convergence analysis with the control systems approach for stability analysis. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/42977]  |
| 专题 | 自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica |
| 推荐引用方式 GB/T 7714 | Zhaorong Zhang,Minyue Fu. Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks[J]. IEEE/CAA Journal of Automatica Sinica,2020,7(3):668-673. |
| APA | Zhaorong Zhang,&Minyue Fu.(2020).Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks.IEEE/CAA Journal of Automatica Sinica,7(3),668-673. |
| MLA | Zhaorong Zhang,et al."Convergence Rate Analysis of Gaussian Belief Propagation for Markov Networks".IEEE/CAA Journal of Automatica Sinica 7.3(2020):668-673. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。