High-Cardinality Hybrid Shaping for 4D Modulation Formats in Optical Communications Optimized via End-to-End Learning

no code implementations • 20 Dec 2021 • Vinícius Oliari, Boris Karanov, Sebastiaan Goossens, Gabriele Liga, Olga Vassilieva, Inwoong Kim, Paparao Palacharla, Chigo Okonkwo, Alex Alvarado

In this paper we carry out a joint optimization of probabilistic (PS) and geometric shaping (GS) for four-dimensional (4D) modulation formats in long-haul coherent wavelength division multiplexed (WDM) optical fiber communications using an auto-encoder framework.

Frequency Logarithmic Perturbation on the Group-Velocity Dispersion Parameter with Applications to Passive Optical Networks

1 code implementation • 10 Mar 2021 • Vinícius Oliari, Erik Agrell, Gabriele Liga, Alex Alvarado

The model can be seen as an improvement of the recently proposed regular perturbation (RP) on the GVD parameter.

Revisiting Efficient Multi-Step Nonlinearity Compensation with Machine Learning: An Experimental Demonstration

no code implementations • 20 Jul 2020 • Vinícius Oliari, Sebastiaan Goossens, Christian Häger, Gabriele Liga, Rick M. Bütler, Menno van den Hout, Sjoerd van der Heide, Henry D. Pfister, Chigo Okonkwo, Alex Alvarado

One guiding principle for previous work on the design of practical nonlinearity compensation schemes is that fewer steps lead to better systems.

BIG-bench Machine Learning