# Approximating the Void: Learning Stochastic Channel Models from Observation with Variational Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1805.06350 · HTML: https://mlsanity.com/paper/1805.06350/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 25 of 25)

- [MIMO Channel Estimation using Score-Based Generative Models](https://mlsanity.com/paper/2204.07122/) (2022)
- [Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs](https://mlsanity.com/paper/2409.17557/) (2024)
- [Generative AI for Physical Layer Communications: A Survey](https://mlsanity.com/paper/2312.05594/) (2023)
- [Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation](https://mlsanity.com/paper/2105.04184/) (2021)
- [MIMO-GAN: Generative MIMO Channel Modeling](https://mlsanity.com/paper/2203.08588/) (2022)
- [Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications](https://mlsanity.com/paper/2207.00300/) (2022)
- [Semantics-Empowered Communication: A Tutorial-cum-Survey](https://mlsanity.com/paper/2212.08487/) (2022)
- [Differentiable and Learnable Wireless Simulation with Geometric Transformers](https://mlsanity.com/paper/2406.14995/) (2024)
- [Diffusion Models for Accurate Channel Distribution Generation](https://mlsanity.com/paper/2309.10505/) (2023)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Few-Shot Domain Adaptation For End-to-End Communication](https://mlsanity.com/paper/2108.00874/) (2021)
- [Two-step Machine Learning Approach for Channel Estimation with Mixed Resolution RF Chains](https://mlsanity.com/paper/2101.09705/) (2021)
- [End-to-End Autoencoder Communications with Optimized Interference Suppression](https://mlsanity.com/paper/2201.01388/) (2021)
- [Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning](https://mlsanity.com/paper/2211.04311/) (2022)
- [Building Semantic Communication System via Molecules: An End-to-End Training Approach](https://mlsanity.com/paper/2404.09595/) (2024)
- [A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning](https://mlsanity.com/paper/2507.01976/) (2025)
- [Residual-Aided End-to-End Learning of Communication System without Known Channel](https://mlsanity.com/paper/2102.10786/) (2021)
- [Sensing-Throughput Tradeoffs with Generative Adversarial Networks for NextG Spectrum Sharing](https://mlsanity.com/paper/2212.13598/) (2022)
- [On the Robustness of Deep Learning-aided Symbol Detectors to Varying Conditions and Imperfect Channel Knowledge](https://mlsanity.com/paper/2401.12645/) (2024)
- [Deep Learning in Wireless Communication Receiver: A Survey](https://mlsanity.com/paper/2501.17184/) (2025)
- [Simplicity is Key: An Unsupervised Pretraining Approach for Sparse Radio Channels](https://mlsanity.com/paper/2505.13055/) (2025)
- [Channel model for end-to-end learning of communications systems: A survey](https://mlsanity.com/paper/2204.03944/) (2022)
- [Modeling of Time-varying Wireless Communication Channel with Fading and Shadowing](https://mlsanity.com/paper/2405.08199/) (2024)
- [How Critical is Site-Specific RAN Optimization? 5G Open-RAN Uplink Air Interface Performance Test and Optimization from Macro-Cell CIR Data](https://mlsanity.com/paper/2410.19565/) (2024)
- [Site-Specific MIMO Channel Generation via Diffusion and Flow Matching: Fidelity, Efficiency, and Downstream Utility](https://mlsanity.com/paper/2606.20098/) (2026)

## Abstract (arXiv)

Channel modeling is a critical topic when considering designing, learning, or evaluating the performance of any communications system. Most prior work in designing or learning new modulation schemes has focused on using highly simplified analytic channel models such as additive white Gaussian noise (AWGN), Rayleigh fading channels or similar. Recently, we proposed the usage of a generative adversarial networks (GANs) to jointly approximate a wireless channel response model (e.g. from real black box measurements) and optimize for an efficient modulation scheme over it using machine learning. This approach worked to some degree, but was unable to produce accurate probability distribution functions (PDFs) representing the stochastic channel response. In this paper, we focus specifically on the problem of accurately learning a channel PDF using a variational GAN, introducing an architecture and loss function which can accurately capture stochastic behavior. We illustrate where our prior method failed and share results capturing the performance of such as system over a range of realistic channel distributions.