Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels

Sergio Hernandez; Svitlana Matsenko; Søren F. Nielsen; Mikkel Schmidt; Christophe Peucheret; Francesco Da Ros; Darko Zibar

doi:10.1109/ICMLCN64995.2025.11140405

Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels

Sergio Hernandez
, Svitlana Matsenko
, Søren F. Nielsen
, Mikkel Schmidt
, Christophe Peucheret
, Francesco Da Ros
, Darko Zibar

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

In linear additive white Gaussian noise (AWGN) channels, optimal signaling schemes can be derived directly from established theoretical models. However, fiber-optic channels are nonlinear, making it challenging to derive optimal signaling schemes analytically. Additionally, the nonlinear behavior of electro-optic modulators and lasers under direct modulation further complicate signal optimization in fiber-optic communication. This paper demonstrates how machine learning techniques can be leveraged to jointly optimize constellations, pulse shaping, and receiver filters for fiber-optic channels. By learning optimal signal strategies tailored to specific channel characteristics, significant performance improvements are achievable.

Original language	English
Title of host publication	Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking
Publisher	IEEE
Publication date	2025
Pages	1-5
Article number	11140405
ISBN (Print)	979-8-3315-2043-4
DOIs	https://doi.org/10.1109/ICMLCN64995.2025.11140405
Publication status	Published - 2025
Event	2025 IEEE International Conference on Machine Learning for Communication and Networking - Barcelona, Spain Duration: 26 May 2025 → 29 May 2025

Conference

Conference	2025 IEEE International Conference on Machine Learning for Communication and Networking
Country/Territory	Spain
City	Barcelona
Period	26/05/2025 → 29/05/2025

Keywords

Filters
Optimization methods
Modulation
Reinforcement learning
Receivers
Optical fiber networks
Lasers and electrooptics
Pulse shaping methods
Optimization
Convergence

Access to Document

10.1109/ICMLCN64995.2025.11140405

OpenUrl availability

Full text

Cite this

Hernandez, S., Matsenko, S., Nielsen, S. F., Schmidt, M., Peucheret, C., Ros, F. D., & Zibar, D. (2025). Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels. In Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking (pp. 1-5). Article 11140405 IEEE. https://doi.org/10.1109/ICMLCN64995.2025.11140405

@inproceedings{7ab64d1f1874420db07d3f7b0e3e46a4,

title = "Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels",

abstract = "In linear additive white Gaussian noise (AWGN) channels, optimal signaling schemes can be derived directly from established theoretical models. However, fiber-optic channels are nonlinear, making it challenging to derive optimal signaling schemes analytically. Additionally, the nonlinear behavior of electro-optic modulators and lasers under direct modulation further complicate signal optimization in fiber-optic communication. This paper demonstrates how machine learning techniques can be leveraged to jointly optimize constellations, pulse shaping, and receiver filters for fiber-optic channels. By learning optimal signal strategies tailored to specific channel characteristics, significant performance improvements are achievable.",

keywords = "Filters, Optimization methods, Modulation, Reinforcement learning, Receivers, Optical fiber networks, Lasers and electrooptics, Pulse shaping methods, Optimization, Convergence",

author = "Sergio Hernandez and Svitlana Matsenko and Nielsen, \{S{\o}ren F.\} and Mikkel Schmidt and Christophe Peucheret and Ros, \{Francesco Da\} and Darko Zibar",

year = "2025",

doi = "10.1109/ICMLCN64995.2025.11140405",

language = "English",

isbn = "979-8-3315-2043-4",

pages = "1--5",

booktitle = "Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking",

publisher = "IEEE",

address = "United States",

note = "2025 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN ; Conference date: 26-05-2025 Through 29-05-2025",

}

Hernandez, S, Matsenko, S, Nielsen, SF, Schmidt, M, Peucheret, C, Ros, FD & Zibar, D 2025, Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels. in Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking., 11140405, IEEE, pp. 1-5, 2025 IEEE International Conference on Machine Learning for Communication and Networking, Barcelona, Spain, 26/05/2025. https://doi.org/10.1109/ICMLCN64995.2025.11140405

Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels. / Hernandez, Sergio; Matsenko, Svitlana; Nielsen, Søren F. et al.
Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking. IEEE, 2025. p. 1-5 11140405.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels

AU - Hernandez, Sergio

AU - Matsenko, Svitlana

AU - Nielsen, Søren F.

AU - Schmidt, Mikkel

AU - Peucheret, Christophe

AU - Ros, Francesco Da

AU - Zibar, Darko

PY - 2025

Y1 - 2025

N2 - In linear additive white Gaussian noise (AWGN) channels, optimal signaling schemes can be derived directly from established theoretical models. However, fiber-optic channels are nonlinear, making it challenging to derive optimal signaling schemes analytically. Additionally, the nonlinear behavior of electro-optic modulators and lasers under direct modulation further complicate signal optimization in fiber-optic communication. This paper demonstrates how machine learning techniques can be leveraged to jointly optimize constellations, pulse shaping, and receiver filters for fiber-optic channels. By learning optimal signal strategies tailored to specific channel characteristics, significant performance improvements are achievable.

AB - In linear additive white Gaussian noise (AWGN) channels, optimal signaling schemes can be derived directly from established theoretical models. However, fiber-optic channels are nonlinear, making it challenging to derive optimal signaling schemes analytically. Additionally, the nonlinear behavior of electro-optic modulators and lasers under direct modulation further complicate signal optimization in fiber-optic communication. This paper demonstrates how machine learning techniques can be leveraged to jointly optimize constellations, pulse shaping, and receiver filters for fiber-optic channels. By learning optimal signal strategies tailored to specific channel characteristics, significant performance improvements are achievable.

KW - Filters

KW - Optimization methods

KW - Modulation

KW - Reinforcement learning

KW - Receivers

KW - Optical fiber networks

KW - Lasers and electrooptics

KW - Pulse shaping methods

KW - Optimization

KW - Convergence

U2 - 10.1109/ICMLCN64995.2025.11140405

DO - 10.1109/ICMLCN64995.2025.11140405

M3 - Article in proceedings

SN - 979-8-3315-2043-4

SP - 1

EP - 5

BT - Proceedings of 2025 IEEE International Conference on Machine Learning for Communication and Networking

PB - IEEE

T2 - 2025 IEEE International Conference on Machine Learning for Communication and Networking

Y2 - 26 May 2025 through 29 May 2025

ER -

Joint Transmitter-Receiver Optimization for Optical Communication over Nonlinear Channels

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this