Geometric Constellation Shaping for Phase-noise Channels Using a Differentiable Blind Phase Search

Abstract

We perform geometric constellation shaping with optimized bit labeling using a binary autoencoder including a differential blind phase search (BPS). Our approach enables full end-to-end training of optical coherent transceivers taking into account the digital signal processing.

arXiv commentSubmitted to the Optical Fiber Communication Conference (OFC) 2022

References in corpus (2)

• End-to-end Deep Learning of Optical Fiber Communications
• Gradient-free training of autoencoders for non-differentiable communication channels

Cited by in corpus (5)

• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Blind Equalization and Channel Estimation in Coherent Optical Communications Using Variational Autoencoders
• Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
• End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
• End-to-end Optimization of Constellation Shaping for Wiener Phase Noise Channels with a Differentiable Blind Phase Search