paper

Geometric Constellation Shaping with Low-complexity Demappers for Wiener Phase-noise Channels

arXiv:2212.02401

Abstract

We show that separating the in-phase and quadrature component in optimized, machine-learning based demappers of optical communications systems with geometric constellation shaping reduces the required computational complexity whilst retaining their good performance.

Submitted to the Optical Fiber Communication Conference (OFC) 2023

Geometric Constellation Shaping with Low-complexity Demappers for Wiener Phase-noise Channels · wovepaper