mlsanityData to 14 Oct 2026

Neural Probabilistic Shaping: Joint Distribution Learning for Optical Fiber Communications

arXiv 2507.16012 ↗First posted 21 Jul 2025cs.LG cs.IT eess.SPcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 25 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

15 of 25 references.

References · 15

  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  3. 2018End-to-end Deep Learning of Optical Fiber Communicationscited by 18
  4. 2019Joint Learning of Geometric and Probabilistic Constellation Shapingcited by 13
  5. 2020Joint Learning of Probabilistic and Geometric Shaping for Coded Modulation Systemscited by 5
  6. 2020Analysis of Nonlinear Fiber Interactions for Finite-Length Constant-Composition Sequencescited by 2
  7. 2021New Lower Bounds on the Capacity of Optical Fiber Channels via Optimized Shaping and Detectioncited by 2
  8. 2022Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communicationcited by 2
  9. 2022Probabilistic Amplitude Shaping and Nonlinearity Tolerance: Analysis and Sequence Selection Methodcited by 2
  10. 2022End-to-end Optimization of Constellation Shaping for Wiener Phase Noise Channels with a Differentiable Blind Phase Searchcited by 2
  11. 2023Sequence-Selection-Based Constellation Shaping for Nonlinear Channelscited by 2
  12. 2024Perturbation-based Sequence Selection for Probabilistic Amplitude Shapingcited by 2
3 more
  1. 2024Cost-Gain Analysis of Sequence Selection for Nonlinearity Mitigationcited by 2
  2. 2024Probabilistic Shaping for Nonlinearity Tolerancecited by 2
  3. 2021Kurtosis-limited Sphere Shaping for Nonlinear Interference Noise Reduction in Optical Channelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Sequential Neural Probabilistic Amplitude Shaping: Learning the Channel's Languagecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
  2. 2022Few-bit Quantization of Neural Networks for Nonlinearity Mitigation in a Fiber Transmission Experiment
  3. 2023Generative AI-Based Probabilistic Constellation Shaping With Diffusion Models
  4. 2023Quantization of Neural Network Equalizers in Optical Fiber Transmission Experiments
  5. 2023Probabilistic Constellation Shaping With Denoising Diffusion Probabilistic Models: A Novel Approach
  6. 2022Deep Learning-Aided Perturbation Model-Based Fiber Nonlinearity Compensation ↗
  7. 2026SoftBinary Coding: A New Information-Theoretic Neural Compression Paradigm
  8. 2024Deep-Learning-Based Channel Estimation for Distributed MIMO with 1-bit Radio-Over-Fiber Fronthaul