# Deep Learning for Channel Coding via Neural Mutual Information Estimation

arXiv: https://arxiv.org/abs/1903.02865 · HTML: https://mlsanity.com/paper/1903.02865/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2019.

## Built on by (most cited first, 14 of 14)

- [Secure Deep-JSCC Against Multiple Eavesdroppers](https://mlsanity.com/paper/2308.02892/) (2023)
- [A Reverse Jensen Inequality Result with Application to Mutual Information Estimation](https://mlsanity.com/paper/2111.06676/) (2021)
- [Neural Capacity Estimators: How Reliable Are They?](https://mlsanity.com/paper/2111.07401/) (2021)
- [MIND: Maximum Mutual Information Based Neural Decoder](https://mlsanity.com/paper/2205.07061/) (2022)
- [Stochastic Mutual Information Gradient Estimation for Dimensionality Reduction Networks](https://mlsanity.com/paper/2105.00191/) (2021)
- [Residual-Aided End-to-End Learning of Communication System without Known Channel](https://mlsanity.com/paper/2102.10786/) (2021)
- [Discriminative Mutual Information Estimators for Channel Capacity Learning](https://mlsanity.com/paper/2107.03084/) (2021)
- [Short Blocklength Wiretap Channel Codes via Deep Learning: Design and Performance Evaluation](https://mlsanity.com/paper/2206.03477/) (2022)
- [Deep Learning in Wireless Communication Receiver: A Survey](https://mlsanity.com/paper/2501.17184/) (2025)
- [Reinforce Security: A Model-Free Approach Towards Secure Wiretap Coding](https://mlsanity.com/paper/2106.00343/) (2021)
- [A Perspective on Neural Capacity Estimation: Viability and Reliability](https://mlsanity.com/paper/2203.11793/) (2022)
- [Data-Driven Estimation of Capacity Upper Bounds](https://mlsanity.com/paper/2205.06471/) (2022)
- [FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training](https://mlsanity.com/paper/2602.01540/) (2026)
- [The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication](https://mlsanity.com/paper/2603.07072/) (2026)

## Abstract (arXiv)

End-to-end deep learning for communication systems, i.e., systems whose encoder and decoder are learned, has attracted significant interest recently, due to its performance which comes close to well-developed classical encoder-decoder designs. However, one of the drawbacks of current learning approaches is that a differentiable channel model is needed for the training of the underlying neural networks. In real-world scenarios, such a channel model is hardly available and often the channel density is not even known at all. Some works, therefore, focus on a generative approach, i.e., generating the channel from samples, or rely on reinforcement learning to circumvent this problem. We present a novel approach which utilizes a recently proposed neural estimator of mutual information. We use this estimator to optimize the encoder for a maximized mutual information, only relying on channel samples. Moreover, we show that our approach achieves the same performance as state-of-the-art end-to-end learning with perfect channel model knowledge.