Revisiting Multi-Step Nonlinearity Compensation with Machine Learning

04/22/2019

∙

by   Christian Häger, et al.

∙

0

∙

share

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.