Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels

arXiv (Cornell University) 2026 Preprint Open access

Read full text
Authors: Mohammad Taha Askari, Lutz Lampe, Amirhossein Ghazisaeidi
DOI: 10.48550/arxiv.2602.02716
Cited by: 0

Abstract

We introduce neural probabilistic amplitude shaping, a joint-distribution learning framework for coherent fiber systems. The proposed scheme provides a 0.5 dB signal-to-noise ratio gain over sequence selection for dual-polarized 64-QAM transmission across a single-span 205 km link.

Fields of Study & Subjects

Optical Network Technologies Advanced Wireless Communication Techniques Optical Wireless Communication Technologies

Publication details

Journal / source
arXiv (Cornell University)
Publication date
2 February 2026
Document type
Preprint