2011/12/02 by Erwin Riegler, Riegler, Erwin, Gunvor Elisabeth Kirkelund +7
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Advanced Wireless Communication Techniques #Algorithm #Applied mathematics #Belief propagation #Channel (broadcasting) #Computer science #DNA and Biological Computing #Decoding methods #Energy (signal processing) #Error Correcting Code Techniques #FOS: Computer and information sciences #Factor graph #Field (mathematics) #Geometry #Graph #Information Theory (cs.IT) #Machine Learning (stat.ML) #Mathematical optimization #Mathematics #Message passing #Orthogonal frequency-division multiplexing #Point (geometry) #Statistics #Telecommunications #Theoretical computer science #cs.IT #math.IT #stat.ML
paper · pdf · doi:10.48550/arxiv.1112.0467
openalex publication_date 2011/12/02 · arxiv created 2012/06/28 · arxiv updated 2012/06/29 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28
We present a joint message passing approach that combines belief propagation\nand the mean field approximation. Our analysis is based on the region-based\nfree energy approximation method proposed by Yedidia et al. We show that the\nmessage passing fixed-point equations obtained with this combination correspond\nto stationary points of a constrained region-based free energy approximation.\nMoreover, we present a convergent implementation of these message passing\nfixedpoint equations provided that the underlying factor graph fulfills certain\ntechnical conditions. In addition, we show how to include hard constraints in\nthe part of the factor graph corresponding to belief propagation. Finally, we\ndemonstrate an application of our method to iterative channel estimation and\ndecoding in an orthogonal frequency division multiplexing (OFDM) system.\n