DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

TL;DR

DeepPolar codes are a novel class of nonlinear large-kernel polar codes designed via deep learning, which improve error correction performance for short-to-medium block lengths by leveraging neural network-parameterized kernels.

Contribution

We introduce DeepPolar codes, a data-driven nonlinear generalization of polar codes that uses neural networks to optimize large kernels for improved error correction.

Findings

DeepPolar codes outperform existing neural and conventional polar codes.

Larger kernels in DeepPolar enhance reliability.

Neural parameterization effectively optimizes kernel design.

Abstract

Progress in designing channel codes has been driven by human ingenuity and, fittingly, has been sporadic. Polar codes, developed on the foundation of Arikan's polarization kernel, represent the latest breakthrough in coding theory and have emerged as the state-of-the-art error-correction code for short-to-medium block length regimes. In an effort to automate the invention of good channel codes, especially in this regime, we explore a novel, non-linear generalization of Polar codes, which we call DeepPolar codes. DeepPolar codes extend the conventional Polar coding framework by utilizing a larger kernel size and parameterizing these kernels and matched decoders through neural networks. Our results demonstrate that these data-driven codes effectively leverage the benefits of a larger kernel size, resulting in enhanced reliability when compared to both existing neural codes and conventional Polar codes.