Deep Broadcast Feedback Codes

TL;DR

This paper explores the use of deep learning to design nonlinear feedback codes for the AWGN broadcast channel, demonstrating improved robustness to feedback noise and better performance at certain conditions compared to traditional analytical codes.

Contribution

It extends learned feedback coding techniques from single-user to broadcast channels and compares their effectiveness with existing analytical schemes.

Findings

Learned codes outperform analytical codes at fixed rate and blocklength with feedback noise.

Deep learning enables nonlinear codes that are more power-efficient and noise-robust.

Analytical codes excel at larger blocklengths and higher SNRs with perfect feedback.

Abstract

Recent advances in deep learning for wireless communications have renewed interest in channel output feedback codes. In the additive white Gaussian broadcast channel with feedback (AWGN-BC-F), feedback can expand the channel capacity region beyond that of the no-feedback case, but linear analytical codes perform poorly with even small amounts of feedback noise. Deep learning enables the design of nonlinear feedback codes that are more resilient to feedback noise. We extend single-user learned feedback codes for the AWGN channel to the broadcast setting, and compare their performance with existing analytical codes, as well as a newly proposed analytical scheme inspired by the learned schemes. Our results show that, for a fixed code rate, learned codes outperform analytical codes at the same blocklength by using power-efficient nonlinear structures and are more robust to feedback noise. Analytical codes scale more easily to larger blocklengths with perfect feedback and surpass learned codes at higher SNRs.