Learned Belief-Propagation Decoding with Simple Scaling and SNR Adaptation

Published

Journal Article

© 2019 IEEE. We consider the weighted belief-propagation (WBP) decoder recently proposed by Nachmani et al. where different weights are introduced for each Tanner graph edge and optimized using machine learning techniques. Our focus is on simple-scaling models that use the same weights across certain edges to reduce the storage and computational burden. The main contribution is to show that simple scaling with few parameters often achieves the same gain as the full parameterization. Moreover, several training improvements for WBP are proposed. For example, it is shown that minimizing average binary cross-entropy is suboptimal in general in terms of bit error rate (BER) and a new "soft-BER" loss is proposed which can lead to better performance. We also investigate parameter adapter networks (PANs) that learn the relation between the signal-to-noise ratio and the WBP parameters. As an example, for the (32, 16) Reed-Muller code with a highly redundant parity-check matrix, training a PAN with soft-BER loss gives near-maximum-likelihood performance assuming simple scaling with only three parameters.

Full Text

Duke Authors

Cited Authors

  • Lian, M; Carpi, F; Hager, C; Pfister, HD

Published Date

  • July 1, 2019

Published In

Volume / Issue

  • 2019-July /

Start / End Page

  • 161 - 165

International Standard Serial Number (ISSN)

  • 2157-8095

Digital Object Identifier (DOI)

  • 10.1109/ISIT.2019.8849419

Citation Source

  • Scopus