# Blind Channel Equalization using Variational Autoencoders

arXiv: https://arxiv.org/abs/1803.01526 · HTML: https://mlsanity.com/paper/1803.01526/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2018.

## Built on by (most cited first, 9 of 9)

- [Generative AI for Physical Layer Communications: A Survey](https://mlsanity.com/paper/2312.05594/) (2023)
- [Autoregressive Belief Propagation for Decoding Block Codes](https://mlsanity.com/paper/2103.11780/) (2021)
- [Variational Autoencoder Leveraged MMSE Channel Estimation](https://mlsanity.com/paper/2205.05345/) (2022)
- [Blind Equalization and Channel Estimation in Coherent Optical Communications Using Variational Autoencoders](https://mlsanity.com/paper/2204.11776/) (2022)
- [EMC2-Net: Joint Equalization and Modulation Classification based on Constellation Network](https://mlsanity.com/paper/2303.10934/) (2023)
- [Variational Autoencoders for Precoding Matrices with High Spectral Efficiency](https://mlsanity.com/paper/2111.15626/) (2021)
- [Interference Cancellation GAN Framework for Dynamic Channels](https://mlsanity.com/paper/2208.08019/) (2022)
- [Novel Phase-Noise-Tolerant Variational-Autoencoder-Based Equalization Suitable for Space-Division-Multiplexed Transmission](https://mlsanity.com/paper/2509.14072/) (2025)
- [Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer](https://mlsanity.com/paper/2609.33695/) (2026)

## Abstract (arXiv)

A new maximum likelihood estimation approach for blind channel equalization, using variational autoencoders (VAEs), is introduced. Significant and consistent improvements in the error rate of the reconstructed symbols, compared to constant modulus equalizers, are demonstrated. In fact, for the channels that were examined, the performance of the new VAE blind channel equalizer was close to the performance of a nonblind adaptive linear minimum mean square error equalizer. The new equalization method enables a significantly lower latency channel acquisition compared to the constant modulus algorithm (CMA). The VAE uses a convolutional neural network with two layers and a very small number of free parameters. Although the computational complexity of the new equalizer is higher compared to CMA, it is still reasonable, and the number of free parameters to estimate is small.