Backward Particle Message Passing

被引：0

作者：

Wymeersch, Henk ^{[1
]}

Irukulapati, Naga V. ^{[1
]}

Sackey, Isaac A. ^{[1
]}

Johannisson, Pontus ^{[1
]}

Agrell, Erik ^{[1
]}

机构：

[1] Chalmers Univ Technol, Gothenburg, Sweden

来源：

2015 IEEE 16TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC) | 2015年

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Particle methods are an established way to represent messages and perform message passing in factor graphs. Despite their common use, there are several cases for which messages are hard to compute, even in linear models. Building on results from Gaussian message passing, we demonstrate how backward particle-based messages can be computed and describe a practical application in the context of fiber-optical communications.

引用

页码：450 / 454

页数：5

共 9 条

[1] Transforming variables using the Dirac generalized function
Au, C
Tam, J
[J]. AMERICAN STATISTICIAN, 1999, 53 (03) : 270 - 272
[2] Regularized estimation of large covariance matrices
Bickel, Peter J.
Levina, Elizaveta
[J]. ANNALS OF STATISTICS, 2008, 36 (01) : 199 - 227
[3] Particle methods as message passing
Dauwels, Justin
Korl, Sascha
Loeliger, Hans-Andrea
[J]. 2006 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, VOLS 1-6, PROCEEDINGS, 2006, : 2052 - +
[4] Irukulapati NV, 2014, 2014 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC)
[5] Stochastic Digital Backpropagation
Irukulapati, Naga V.
Wymeersch, Henk
Johannisson, Pontus
Agrell, Erik
[J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2014, 62 (11) : 3956 - 3968
[6] An introduction to factor graphs
Loeliger, HA
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 2004, 21 (01) : 28 - 41
[7] The factor graph approach to model-based signal processing
Loeliger, Hans-Andrea
Dauwels, Justin
Hu, Junli
Korl, Sascha
Ping, Li
Kschischang, Frank R.
[J]. PROCEEDINGS OF THE IEEE, 2007, 95 (06) : 1295 - 1322
[8] Density estimation
Sheather, SJ
[J]. STATISTICAL SCIENCE, 2004, 19 (04) : 588 - 597
[9] Sudderth EB, 2003, PROC CVPR IEEE, P605

← 1 →