English

Wideband and Entropy-Aware Deep Soft Bit Quantization

Signal Processing 2021-10-20 v1 Information Theory Machine Learning math.IT

Abstract

Deep learning has been recently applied to physical layer processing in digital communication systems in order to improve end-to-end performance. In this work, we introduce a novel deep learning solution for soft bit quantization across wideband channels. Our method is trained end-to-end with quantization- and entropy-aware augmentations to the loss function and is used at inference in conjunction with source coding to achieve near-optimal compression gains over wideband channels. To efficiently train our method, we prove and verify that a fixed feature space quantization scheme is sufficient for efficient learning. When tested on channel distributions never seen during training, the proposed method achieves a compression gain of up to 10%10 \% in the high SNR regime versus previous state-of-the-art methods. To encourage reproducible research, our implementation is publicly available at https://github.com/utcsilab/wideband-llr-deep.

Keywords

Cite

@article{arxiv.2110.09541,
  title  = {Wideband and Entropy-Aware Deep Soft Bit Quantization},
  author = {Marius Arvinte and Jonathan I. Tamir},
  journal= {arXiv preprint arXiv:2110.09541},
  year   = {2021}
}
R2 v1 2026-06-24T06:59:15.117Z