Nonlinear Posterior-Mean Feedback Codes for AWGN Channels
Abstract
Feedback can improve the reliability of communication over additive white Gaussian noise (AWGN) channels. Classical feedback codes are interpretable, or easy to understand, but often rely on linear estimation, while deep-learned feedback codes can achieve strong performance but require many learned parameters and are often black boxes that are difficult to interpret. In this work, we propose a new 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. This scheme is analytically described, but a few learned parameters related to power allocation, and hence we consider this an ``interpretable,'' or human-understandable code. 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.
Related
- KKTCode: Asymptotically Optimal Linear Codes for Noisy Feedback AWGN Channels
- Joint Identification, Transmission, and Sensing over State-Dependent Channels with Noiseless Feedback
- Log Density Spectrum Based Decoding of Polar Codes for Channels with Strong Phase Noise
- Feedback Capacity of Stationary Gaussian Channels: An Optimal Schalkwijk-Kailath Scheme
- Marker-Delimited Codes for Short-Blocklength, High-Rate Coding over Multi-Read Edit Channels
BibTeX
@misc{zhou2026nonlinear,
title = {{Nonlinear Posterior-Mean Feedback Codes for AWGN Channels}},
author = {Yingyao Zhou and Natasha Devroye and Milos Zefran and Gyorgy Turan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05555},
eprint = {2610.05555},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05555},
}
RIS
TY - UNPB
TI - Nonlinear Posterior-Mean Feedback Codes for AWGN Channels
AU - Yingyao Zhou
AU - Natasha Devroye
AU - Milos Zefran
AU - Gyorgy Turan
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.05555
UR - https://arxiv.org/abs/2610.05555
AB - Feedback can improve the reliability of communication over additive white Gaussian noise (AWGN) channels. Classical feedback codes are interpretable, or easy to understand, but often rely on linear estimation, while deep-learned feedback codes can achieve strong performance but require many learned parameters and are often black boxes that are difficult to interpret. In this work, we propose a new 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. This scheme is analytically described, but a few learned parameters related to power allocation, and hence we consider this an ``interpretable,'' or human-understandable code. 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.
ER -