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

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.

References in corpus (1)

• Polarization-ring-switching for nonlinearity-tolerant geometrically-shaped four-dimensional formats maximizing generalized mutual information

Cited by in corpus (9)

• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Geometrically-Shaped Multi-Dimensional Modulation Formats in Coherent Optical Transmission Systems
• Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
• Analysis and Experimental Demonstration of Orthant-Symmetric Four-dimensional 7 bit/4D-sym Modulation for Optical Fiber Communication
• End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
• Temporal Energy Analysis of Symbol Sequences for Fiber Nonlinear Interference Modelling via Energy Dispersion Index
• Gradient-free training of autoencoders for non-differentiable communication channels
• End-to-end Optimization of Constellation Shaping for Wiener Phase Noise Channels with a Differentiable Blind Phase Search
• Low-complexity Voronoi shaping for the Gaussian channel