{"ID":2892437,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16012","arxiv_id":"2507.16012","title":"Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications","abstract":"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.","short_abstract":"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 sing...","url_abs":"https://arxiv.org/abs/2507.16012","url_pdf":"https://arxiv.org/pdf/2507.16012v1","authors":"[\"Mohammad Taha Askari\",\"Lutz Lampe\",\"Amirhossein Ghazisaeidi\"]","published":"2025-07-21T19:21:51Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.IT\",\"eess.SP\"]","methods":"[]","has_code":false}