Gradient Descent Bit-Flipping Decoding with Momentum

TL;DR

This paper introduces a momentum-enhanced gradient descent bit-flipping decoding method that improves error correction performance, especially in high-connectivity graphs, approaching or surpassing belief-propagation decoding in the error-floor region.

Contribution

It presents a novel GDBF decoding algorithm with momentum, significantly enhancing decoding performance over traditional methods.

Findings

GDBF with momentum approaches belief-propagation performance

Outperforms in the error-floor region for high connectivity graphs

Potentially surpasses belief-propagation in certain scenarios

Abstract

In this paper, we propose a Gradient Descent Bit-Flipping (GDBF) decoding with momentum, which considers past updates to provide inertia to the decoding process. We show that GDBF or randomized GDBF decoders with momentum may closely approach the floating-point Belief-Propagation decoding performance, and even outperform it in the error-floor region, especially for graphs with high connectivity degree.