English

Revisiting Multi-Step Nonlinearity Compensation with Machine Learning

Signal Processing 2019-04-23 v1 Artificial Intelligence Information Theory math.IT Machine Learning

Abstract

For the efficient compensation of fiber nonlinearity, one of the guiding principles appears to be: fewer steps are better and more efficient. We challenge this assumption and show that carefully designed multi-step approaches can lead to better performance-complexity trade-offs than their few-step counterparts.

Keywords

Cite

@article{arxiv.1904.09807,
  title  = {Revisiting Multi-Step Nonlinearity Compensation with Machine Learning},
  author = {Christian Häger and Henry D. Pfister and Rick M. Bütler and Gabriele Liga and Alex Alvarado},
  journal= {arXiv preprint arXiv:1904.09807},
  year   = {2019}
}

Comments

4 pages, 3 figures, This is a preprint of a paper submitted to the 2019 European Conference on Optical Communication

R2 v1 2026-06-23T08:46:12.194Z