Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels

Mohammad Taha Askari; Lutz Lampe; Amirhossein Ghazisaeidi

Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels

Machine Learning 2026-02-04 v1 Signal Processing

Authors: Mohammad Taha Askari , Lutz Lampe , Amirhossein Ghazisaeidi

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.

Keywords

coded modulation wireless communication wireless channel

Cite

@article{arxiv.2602.02716,
  title  = {Neural Probabilistic Amplitude Shaping for Nonlinear Fiber Channels},
  author = {Mohammad Taha Askari and Lutz Lampe and Amirhossein Ghazisaeidi},
  journal= {arXiv preprint arXiv:2602.02716},
  year   = {2026}
}

Comments

3 pages, 2 figures, Submitted to Optical Fiber Communication Conference (OFC) 2026

Related papers

View all related →

Machine Learning · Computer Science

Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications