Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications
This addresses the problem of improving data transmission efficiency in optical fiber communications, though it appears incremental as it builds on existing shaping methods.
The paper tackles probabilistic shaping for nonlinear fiber channels by learning the joint symbol distribution, achieving a 0.3-bits/2D gain in information rate over an optimized marginal distribution for 64-QAM transmission over a 205 km link.
We present an autoregressive end-to-end learning approach for probabilistic shaping on nonlinear fiber channels. Our proposed scheme learns the joint symbol distribution and provides a 0.3-bits/2D achievable information rate gain over an optimized marginal distribution for dual-polarized 64-QAM transmission over a single-span 205 km link.