End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 1.
4 papers.
- 2021End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Modelcited by 2
- 2021End-to-End Learning of Joint Geometric and Probabilistic Constellation Shapingcited by 2
- 2022Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learningcited by 2
- 2024Friendly Attacks to Improve Channel Coding Reliabilitycited by 1
- 2024Friendly Attacks to Improve Channel Coding Reliability25 Jan 2024
- 2022Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning8 Nov 2022
- 2021End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping9 Dec 2021
- 2021End-to-End Deep Learning of Long-Haul Coherent Optical Fiber Communications via Regular Perturbation Model26 Jul 2021