Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915404073402368 |
|---|---|
| author | Askari, Mohammad Taha Lampe, Lutz Ghazisaeidi, Amirhossein |
| author_facet | Askari, Mohammad Taha Lampe, Lutz Ghazisaeidi, Amirhossein |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications Askari, Mohammad Taha Lampe, Lutz Ghazisaeidi, Amirhossein Machine Learning Information Theory Signal Processing 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. |
| title | Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications |
| topic | Machine Learning Information Theory Signal Processing |
| url | https://arxiv.org/abs/2507.16012 |