Several machine learning inspired methods for perturbation-based fiber nonlinearity (PBNLC) compensation have been presented in recent literature. We critically revisit acclaimed benefits of those over non-learned methods. Numerical results suggest that learned linear processing of perturbation triplets of PB-NLC is preferable over feedforward neural-network solutions.
@article{arxiv.2210.03440,
title = {Learning for Perturbation-Based Fiber Nonlinearity Compensation},
author = {Shenghang Luo and Sunish Kumar Orappanpara Soman and Lutz Lampe and Jeebak Mitra and Chuandong Li},
journal= {arXiv preprint arXiv:2210.03440},
year = {2022}
}