# End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth

arXiv: https://arxiv.org/abs/2106.00431 · HTML: https://mlsanity.com/paper/2106.00431/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2021.

## Built on by (most cited first, 1 of 1)

- [Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning](https://mlsanity.com/paper/2211.04311/) (2022)

## Abstract (arXiv)

We propose an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors. This constellation maintains shaping gain in mutual information (up to 0.3 bits/symbol) with respect to QAM over various SNR and laser linewidth values.