Journal article ยท Preprint article
Gradient-free training of autoencoders for non-differentiable communication channels
Department of Photonics Engineering, Technical University of Denmark1
Machine Learning in Photonic Systems, Department of Photonics Engineering, Technical University of Denmark2
Ultra-fast Optical Communication, Department of Photonics Engineering, Technical University of Denmark3
Coding and Visual Communication, Department of Photonics Engineering, Technical University of Denmark4
Centre of Excellence for Silicon Photonics for Optical Communications, Centers, Technical University of Denmark5
Training of autoencoders using the back-propagation algorithm is challenging for non-differential channel models or in an experimental environment where gradients cannot be computed. In this paper, we study a gradient-free training method based on the cubature Kalman filter. To numerically validate the method, the autoencoder is employed to perform geometric constellation shaping on differentiable communication channels, showing the same performance as the back-propagation algorithm.
Further investigation is done on a non-differentiable communication channel that includes: laser phase noise, additive white Gaussian noise and blind phase search-based phase noise compensation. Our results indicate that the autoencoder can be successfully optimized using the proposed training method to achieve better robustness to residual phase noise with respect to standard constellation schemes such as Quadrature Amplitude Modulation and Iterative Polar Modulation for the considered conditions.
Language: | English |
---|---|
Year: | 2021 |
Pages: | 6381-6391 |
ISSN: | 15582213 and 07338724 |
Types: | Journal article and Preprint article |
DOI: | 10.1109/JLT.2021.3103339 |
ORCIDs: | Jovanovic, Ognjen , Yankov, Metodi Plamenov , Da Ros, Francesco and Zibar, Darko |
Cubature Kalman filter End-to-end learning Geometric constellation shaping Optical fiber communication Phase noise