Guardado en:
Detalles Bibliográficos
Autores principales: Lai, Wenwei, Shao, Yulin, Ding, Yu, Gunduz, Deniz
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.08481
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929589628960768
author Lai, Wenwei
Shao, Yulin
Ding, Yu
Gunduz, Deniz
author_facet Lai, Wenwei
Shao, Yulin
Ding, Yu
Gunduz, Deniz
contents Variable-length feedback coding has the potential to significantly enhance communication reliability in finite block length scenarios by adapting coding strategies based on real-time receiver feedback. Designing such codes, however, is challenging. While deep learning (DL) has been employed to design sophisticated feedback codes, existing DL-aided feedback codes are predominantly fixed-length and suffer performance degradation in the high code rate regime, limiting their adaptability and efficiency. This paper introduces deep variable-length feedback (DeepVLF) code, a novel DL-aided variable-length feedback coding scheme. By segmenting messages into multiple bit groups and employing a threshold-based decoding mechanism for independent decoding of each bit group across successive communication rounds, DeepVLF outperforms existing DL-based feedback codes and establishes a new benchmark in feedback channel coding.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variable-Length Feedback Codes via Deep Learning
Lai, Wenwei
Shao, Yulin
Ding, Yu
Gunduz, Deniz
Information Theory
Variable-length feedback coding has the potential to significantly enhance communication reliability in finite block length scenarios by adapting coding strategies based on real-time receiver feedback. Designing such codes, however, is challenging. While deep learning (DL) has been employed to design sophisticated feedback codes, existing DL-aided feedback codes are predominantly fixed-length and suffer performance degradation in the high code rate regime, limiting their adaptability and efficiency. This paper introduces deep variable-length feedback (DeepVLF) code, a novel DL-aided variable-length feedback coding scheme. By segmenting messages into multiple bit groups and employing a threshold-based decoding mechanism for independent decoding of each bit group across successive communication rounds, DeepVLF outperforms existing DL-based feedback codes and establishes a new benchmark in feedback channel coding.
title Variable-Length Feedback Codes via Deep Learning
topic Information Theory
url https://arxiv.org/abs/2411.08481