Blind Decoding-Metric Estimation for Probabilistic Shaping via Expectation Maximization
Fabian Steiner, Patrick Schulte, Georg Böcherer · arXiv (Cornell University) · 2018
An unsupervised learning approach based on expectation maximization is proposed to obtain the parameters of a soft decision forward error correction decoding metric for probabilistic shaping. The algorithm depends only on the channel observations and does not require transmitted data.