# ADMM-based Decoder for Binary Linear Codes Aided by Deep Learning

arXiv: https://arxiv.org/abs/2002.07601 · HTML: https://mlsanity.com/paper/2002.07601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Grassmannian learning mutual subspace method for image set recognition](https://mlsanity.com/paper/2111.04352/) (2021)
- [A recipe of training neural network-based LDPC decoders](https://mlsanity.com/paper/2205.00481/) (2022)

## Abstract (arXiv)

Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the alternating direction method of multipliers (ADMM)-penalized decoder. In addition, we propose two improved versions of the proposed network. The first one transforms the penalty parameter into a set of iteration-dependent ones, and the second one adopts a specially designed penalty function, which is based on a piecewise linear function with adjustable slopes. Numerical results show that the resulting DL-aided decoders outperform the original ADMM-penalized decoder for various low density parity check (LDPC) codes with similar computational complexity.