Deep Learning-Based Quantization of L-Values for Gray-Coded Modulation
This work addresses memory efficiency in communication systems, particularly for LDPC-coded scenarios, but is incremental as it builds on existing quantization methods with specific improvements.
The paper tackles the problem of compressing log-likelihood ratio (L-value) storage for quadrature amplitude modulation by introducing a deep autoencoder-based quantization scheme, achieving up to a two-fold reduction in memory footprint with performance losses smaller than 0.1 dB at less than two effective bits per L-value.
In this work, a deep learning-based quantization scheme for log-likelihood ratio (L-value) storage is introduced. We analyze the dependency between the average magnitude of different L-values from the same quadrature amplitude modulation (QAM) symbol and show they follow a consistent ordering. Based on this we design a deep autoencoder that jointly compresses and separately reconstructs each L-value, allowing the use of a weighted loss function that aims to more accurately reconstructs low magnitude inputs. Our method is shown to be competitive with state-of-the-art maximum mutual information quantization schemes, reducing the required memory footprint by a ratio of up to two and a loss of performance smaller than 0.1 dB with less than two effective bits per L-value or smaller than 0.04 dB with 2.25 effective bits. We experimentally show that our proposed method is a universal compression scheme in the sense that after training on an LDPC-coded Rayleigh fading scenario we can reuse the same network without further training on other channel models and codes while preserving the same performance benefits.