Metraipolis › archive › dc_23ffb7ec1909

Nonlinear Posterior-Mean Feedback Codes for AWGN Channels — arXiv:2610.05555

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.05555
License (as archived)
CC0-1.0
Archived
2026-10-06T16:59:13.583Z
SHA-256 of the archived text
b32a2b77f732f685c47f41306752f172d4b5b27002180b4f2f3580e6de610a07
Stable URL of this page
https://metraipolis.com/documento/dc_23ffb7ec1909

How to cite

Nonlinear Posterior-Mean Feedback Codes for AWGN Channels — arXiv:2610.05555 — arXiv (en), https://arxiv.org/abs/2610.05555 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23ffb7ec1909 (Metraipolis archive dc_23ffb7ec1909, sha256 b32a2b77f732f685c47f41306752f172d4b5b27002180b4f2f3580e6de610a07)
BibTeX
@misc{dc23ffb7ec1909,
  title = {Nonlinear Posterior-Mean Feedback Codes for AWGN Channels — arXiv:2610.05555},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.05555},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23ffb7ec1909; sha256 b32a2b77f732f685c47f41306752f172d4b5b27002180b4f2f3580e6de610a07},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.05555. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feedback can improve the reliability of communication over additive white Gaussian noise (AWGN) channels. Classical feedback codes are interpretable but often rely on linear estimation, while deep-learned feedback codes can achieve strong performance but require many learned parameters and are difficult to interpret. In this work, we propose an interpretable posterior-mean feedback coding framework for AWGN channels with feedback. The proposed scheme uses posterior-mean refinement to construct nonlinear feedback codes under both noiseless passive feedback and noisy active feedback, with maximum a posteriori (MAP) decoding at the receiver. We further develop a projection-based design to improve robustness under noisy feedback and support larger message sizes. Numerical results show that the proposed schemes achieve strong finite-blocklength performance and outperform several analytical and learned feedback coding baselines, while using only a small number of learned design parameters.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.IT, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2610.05555 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T15:24:20.170Z dalla pagina https://arxiv.org/list/math.IT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).