Geometric Constellation Shaping for Phase-noise Channels Using a Differentiable Blind Phase Search
Andrej Rode, Benedikt Geiger, Laurent Schmalen

TL;DR
This paper introduces a method for geometric constellation shaping combined with optimized bit labeling, utilizing a differentiable blind phase search to enable end-to-end training of optical coherent transceivers considering digital signal processing.
Contribution
It presents a novel end-to-end training approach for optical transceivers that integrates geometric constellation shaping with a differentiable blind phase search.
Findings
Improved constellation shaping performance for phase-noise channels
Enhanced bit labeling optimization in optical communication systems
Demonstrated feasibility of end-to-end training including digital signal processing
Abstract
We perform geometric constellation shaping with optimized bit labeling using a binary autoencoder including a differential blind phase search (BPS). Our approach enables full end-to-end training of optical coherent transceivers taking into account the digital signal processing.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
