An Analysis of Turbo Decoding with Gaussian Densities

Abstract

We provide an analysis of the turbo decoding algorithm (TDA) in a setting involving Gaussian densities. In this context, we are able to show that the algorithm converges and that - somewhat surprisingly - though the density generated by the TDA may differ significantly from the desired posterior density, the means of these two densities coincide.

Cite

Text

Rusmevichientong and Van Roy. "An Analysis of Turbo Decoding with Gaussian Densities." Neural Information Processing Systems, 1999.

Markdown

[Rusmevichientong and Van Roy. "An Analysis of Turbo Decoding with Gaussian Densities." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/rusmevichientong1999neurips-analysis/)

BibTeX

@inproceedings{rusmevichientong1999neurips-analysis,
  title     = {{An Analysis of Turbo Decoding with Gaussian Densities}},
  author    = {Rusmevichientong, Paat and Van Roy, Benjamin},
  booktitle = {Neural Information Processing Systems},
  year      = {1999},
  pages     = {575-581},
  url       = {https://mlanthology.org/neurips/1999/rusmevichientong1999neurips-analysis/}
}