Learning Quantization in LDPC Decoders

• Published in: 2022 IEEE Globecom Workshops (GC Wkshps) pp. 467 - 472
• Main Authors: Geiselhart, Marvin, Elkelesh, Ahmed, Clausius, Jannis, Liang, Fei, Xu, Wen, Liang, Jing, Brink, Stephan Ten
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.12.2022
• Subjects: Conferences; Decoding; Learning systems; Parity check codes; Quantization (signal); Simulation; Training
• DOI: 10.1109/GCWkshps56602.2022.10008635

Finding optimal message quantization is a key requirement for low complexity belief propagation (BP) decoding. To this end, we propose a floating-point surrogate model that imitates quantization effects as additions of uniform noise, whose amplitudes are trainable variables. We verify that the surrogate model closely matches the behavior of a fixed-point implementation and propose a hand-crafted loss function to realize a trade-off between complexity and error-rate performance. A deep learning-based method is then applied to optimize the message bitwidths. Moreover, we show that parameter sharing can both ensure implementation-friendly solutions and results in faster training convergence than independent parameters. We provide simulation results for 5G low-density parity-check (LDPC) codes and report an error-rate performance within 0.2 dB of floating-point decoding at an average message quantization bitwidth of 3.1 bits. In addition, we show that the learned bitwidths also generalize to other code rates and channels