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

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

51 Citations (SciVal)
80 Downloads (Pure)

Abstract

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.

Original languageEnglish
Title of host publication2020 Optical Fiber Communications Conference and Exhibition, OFC 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers
Chapter3
ISBN (Electronic)9781943580712
ISBN (Print)9781943580712
DOIs
Publication statusPublished - 13 May 2020
Event2020 Optical Fiber Communications Conference and Exhibition, OFC 2020 - San Diego, United States
Duration: 8 Mar 202012 Mar 2020
https://www.ofcconference.org/en-us/home/

Conference

Conference2020 Optical Fiber Communications Conference and Exhibition, OFC 2020
Abbreviated titleOFC 2020
Country/TerritoryUnited States
CitySan Diego
Period8/03/2012/03/20
Internet address

Funding

Acknowledgements: This work was funded by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant no. 749798 and the ERC grant no. 757791, the National Natural Science Foundation of China (NSFC) under grant no. 61701155, the Fundamental Research Funds for the Central Universities under grant no. JZ2019HGBZ0130, the Netherlands Organisation for Scientific Research (NWO) via the VIDI project ICONIC under grant no. 15685, and the Swedish Research Council under grant no. 2017-03702.

FundersFunder number
European Union 's Horizon 2020 - Research and Innovation Framework Programme757791
Marie Skłodowska‐Curie749798
European Research Council
National Natural Science Foundation of China61701155
Nederlandse Organisatie voor Wetenschappelijk Onderzoek15685
Vetenskapsrådet2017-03702
Fundamental Research Funds for the Central UniversitiesJZ2019HGBZ0130

    Fingerprint

    Dive into the research topics of 'End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information'. Together they form a unique fingerprint.

    Cite this