mlsanityData to 7 Oct 2026

Model-free Training of End-to-end Communication Systems

arXiv 1812.05929 ↗First posted 14 Dec 2018cs.IT cs.AI math.ITcited by 29

Not on the map. Why?

Abstract (arXiv)

The idea of end-to-end learning of communication systems through neural network-based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates this problem. The algorithm enables training of communication systems with an unknown channel model or with non-differentiable components. It iterates between training of the receiver using the true gradient, and training of the transmitter using an approximation of the gradient. We show that this approach works as well as model-based training for a variety of channels and tasks. Moreover, we demonstrate the algorithm's practical viability through hardware implementation on software-defined radios where it achieves state-of-the-art performance over a coaxial cable and wireless channel.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 8; 2023: 7; 2024: 4; 2025: 2.

29 papers.

Sort:

By area:

  1. 2021Reinforcement Learning-powered Semantic Communication via Semantic Similaritycited by 15
  2. 2021Waveform Learning for Next-Generation Wireless Communication Systemscited by 10
  3. 2023Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communicationscited by 10
  4. 2022Semantics-Empowered Communication: A Tutorial-cum-Surveycited by 8
  5. 2023Diffusion Models for Wireless Communicationscited by 6
  6. 2024Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applicationscited by 6
  7. 2022Bit Error and Block Error Rate Training for ML-Assisted Communicationcited by 5
  8. 2022Channel charting based beamformingcited by 5
  9. 2024Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challengescited by 5
  10. 2021CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexitycited by 3
  11. 2021Few-Shot Domain Adaptation For End-to-End Communicationcited by 3
  12. 2021End-to-End Learning for Uplink MU-SIMO Joint Transmitter and Non-Coherent Receiver Design in Fading Channelscited by 2
17 more
  1. 2022Hybrid Neural Coded Modulation: Design and Training Methodscited by 2
  2. 2023Model-free Reinforcement Learning of Semantic Communication by Stochastic Policy Gradientcited by 2
  3. 2023Semantic Multi-Resolution Communicationscited by 2
  4. 2023Generative AI-Based Probabilistic Constellation Shaping With Diffusion Modelscited by 2
  5. 2024Building Semantic Communication System via Molecules: An End-to-End Training Approachcited by 2
  6. 2021Residual-Aided End-to-End Learning of Communication System without Known Channelcited by 1
  7. 2022Theoretical Analysis of Deep Neural Networks in Physical Layer Communicationcited by 1
  8. 2022DUIDD: Deep-Unfolded Interleaved Detection and Decoding for MIMO Wireless Systemscited by 1
  9. 2023SICNN: Soft Interference Cancellation Inspired Neural Network Equalizerscited by 1
  10. 2024Data-Driven Symbol Detection for Intersymbol Interference Channels with Bursty Impulsive Noisecited by 1
  11. 2021Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channelscited by 0
  12. 2021Blind Coherent Preamble Detection via Neural Networkscited by 0
  13. 2022A Perspective on Neural Capacity Estimation: Viability and Reliabilitycited by 0
  14. 2022Channel model for end-to-end learning of communications systems: A surveycited by 0
  15. 2023Denoising Diffusion Probabilistic Models for Hardware-Impaired Communicationscited by 0
  16. 2025Cross-Technology Interference: Detection, Avoidance, and Coexistence Mechanisms in the ISM Bandscited by 0
  17. 2025Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communicationscited by 0