ITSPMLJul 19, 2019

End-to-end Learning for GMI Optimized Geometric Constellation Shape

arXiv:1907.08535v162 citations
Originality Incremental advance
AI Analysis

This work addresses incremental improvements in optical communication systems by enhancing data transmission efficiency for engineers and researchers.

The paper tackled the problem of optimizing geometric constellation shapes and bit mappings for improved Generalized Mutual Information (GMI), achieving up to 0.2 bits per QAM symbol gain across various data rates and under transceiver impairments, with no additional cost compared to conventional methods.

Autoencoder-based geometric shaping is proposed that includes optimizing bit mappings. Up to 0.2 bits/QAM symbol gain in GMI is achieved for a variety of data rates and in the presence of transceiver impairments. The gains can be harvested with standard binary FEC at no cost w.r.t. conventional BICM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes