Revisiting multi-step nonlinearity compensation with machine learning


Journal Article

© 2019 Institution of Engineering and Technology. All rights reserved. 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.

Duke Authors

Cited Authors

  • Häger, C; Pfister, HD; Bütler, RM; Liga, G; Alvarado, A

Published Date

  • January 1, 2019

Published In

  • Iet Conference Publications

Volume / Issue

  • 2019 / CP765

Citation Source

  • Scopus