End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information

Kadir Gumus, Alex Alvarado, Bin Chen, Christian Hager, Erik Agrell

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Samenvatting

GMI-based end-to-end learning is shown to be highly nonconvex. We apply gradient descent initialized with Gray-labeled APSK constellations directly to the constellation coordinates. State-of-the-art constellations in 2D and 4D are found providing reach increases up to 26% w.r.t. to QAM.

Originele taal-2Engels
Titel2020 Optical Fiber Communications Conference and Exhibition, OFC 2020 - Proceedings
UitgeverijInstitute of Electrical and Electronics Engineers
Hoofdstuk3
ISBN van elektronische versie9781943580712
StatusGepubliceerd - 13 mei 2020
Evenement2020 Optical Fiber Communications Conference and Exhibition, OFC 2020 - San Diego, Verenigde Staten van Amerika
Duur: 8 mrt 202012 mrt 2020

Congres

Congres2020 Optical Fiber Communications Conference and Exhibition, OFC 2020
LandVerenigde Staten van Amerika
StadSan Diego
Periode8/03/2012/03/20

Vingerafdruk Duik in de onderzoeksthema's van 'End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Gumus, K., Alvarado, A., Chen, B., Hager, C., & Agrell, E. (2020). End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information. In 2020 Optical Fiber Communications Conference and Exhibition, OFC 2020 - Proceedings [9083181] Institute of Electrical and Electronics Engineers. https://ieeexplore.ieee.org/document/9083181